All authors
Claude Skills by uncovertechtalent
github.com/uncovertechtalent71 skills0 installs42 views
- Agent HarnessSet up the shared harness for an engineering team's coding agents: shared settings with narrow permissions, the instruction file, the plugin list, MCP servers with secrets from the environment, hooks, and docs/agents.md naming the owner. Use when a team starts using coding agents, when each developer runs a different setup, or after an agent did something nobody allowed. Activates on "/agent-harness", "set up our agents", "shared agent settings", "agent permissions", "harden the agent setup".Votes: 0GitHub stars: 2
- CoordinatorRun a coordinator session that routes work to worker sessions or subagents and verifies their artifacts, with all state in files: a ledger of tasks, briefs that name files and done criteria, caps on parallel workers, and resume after a stop. Use when one person runs several agent sessions at once, when a batch of tasks is too big for one session, or after a session limit cut work off. Activates on "/coordinator", "coordinate these sessions", "split this across agents", "resume the batch", "ru...Votes: 0GitHub stars: 2
- MeteringMeter coding-agent spend per API request: send Claude Code telemetry to the observability stack, sum cost and tokens from the per-request api_request events in Loki, show them on a dashboard, and alert when spend passes an hourly budget. Use when agent spend is a line on the invoice nobody can break down, or before a team scales its agent use. Activates on "/metering", "meter agent spend", "what do our agents cost", "agent cost dashboard", "agent spend alert".Votes: 0GitHub stars: 2
- Answer ProbeAsk AI search engines and assistants a fixed, versioned query set and record per answer whether it names the entity, links it and states the expected facts correctly, with dated JSON results and a trend over runs of the same query set version. Use when a team wants to know whether AI answers name and cite its site, before and after a change, without third-party tracking tools. Activates on "/answer-probe", "probe the AI engines", "do AI answers cite us", "run the answer probe", "AI search vis...Votes: 0GitHub stars: 2
- Llms TxtWrite and maintain llms.txt at the site root: a title, a short summary and sections of links with one line per page, built from the site's own pages and kept in step with the sitemap. Use when the owners of a site want a plain index for agents and language models that read it, or when pages were added or removed since the file was last written. Activates on "/llms-txt", "write llms.txt", "update llms.txt", "is llms.txt in sync", "llms.txt out of date".Votes: 0GitHub stars: 2
- Prediction HashWrite a dated prediction file before a page goes live, compute its sha256, add the line to predictions/HASHES.txt and commit both, so a third party can check that the prediction was not changed after the result came in. Use when a page makes a claim about a future result (an answer engine experiment, a probe reading, an evaluation) and the claim must be fixed in public before the page goes live. Activates on "/prediction-hash", "hash a prediction", "preregister this", "freeze the prediction",...Votes: 0GitHub stars: 2
- Structured DataAdd JSON-LD structured data to every page of a site, one graph per page type (Organization or Person, WebSite, Article, BreadcrumbList, and FAQPage only where the page shows real questions), generated from one source, parsed as JSON and checked against the visible page. Use when a site has no structured data, carries hand-written blocks that drift from the pages, or marks up text a reader cannot see. Activates on "/structured-data", "add JSON-LD", "schema.org markup", "structured data for AI ...Votes: 0GitHub stars: 2
- Ai Act TriageTriage every AI use in a register under the EU AI Act: classify each one as a prohibited practice (Art 5), high-risk (Annex III use case or Annex I product safety), transparency obligations (Art 50) or minimal, record provider obligations for general-purpose AI models, and note the date from which each obligation applies. Prepares the question for legal review. Use when a team builds, buys or ships an AI feature, or before a customer or auditor asks for the AI inventory. Activates on "/ai-act...Votes: 0GitHub stars: 2
- Control MapMap the team's existing controls and their evidence to ISO 27001 Annex A control numbers, TISAX (VDA ISA question numbers), NIS2 articles and GDPR articles, in one CSV with control id, owner, evidence link, status and gap per row. Numbers only: the client adds titles from their own licensed copies. Use when a team prepares for an audit, a customer questionnaire or a TISAX assessment, or needs to know which requirements have no control yet. Activates on "/control-map", "map our controls", "con...Votes: 0GitHub stars: 2
- Legal BaselineSet up the legal baseline of a website: an Impressum under German law (§ 5 DDG), a privacy page with the information of GDPR Art 13, a /.well-known/security.txt with Contact and Expires (RFC 9116), and no third-party requests on page load (fonts, scripts and styles self-hosted, no analytics without consent). Adds gate checks for security.txt and third-party loads. Use when a team launches or audits a public website, or a page loads fonts, scripts or embeds from other hosts. Activates on "/leg...Votes: 0GitHub stars: 2
- AdrRecord one decision as a numbered architecture decision record (ADR) with context, decision and consequences, from an accepted or rejected RFC or directly for a small decision. Use when a decision is made, from a closed RFC or directly, and the team needs a record of it. Handles supersede links on both records and keeps the index in docs/decisions/index.md current. Never overwrites a file. Activates on "/adr", "write an ADR", "record a decision", "record this decision", "new decision record",...Votes: 0GitHub stars: 2
- Decision Log ReviewSweep the decision log in docs/decisions/ and report what needs attention: records missing status, owner or date, proposed ADRs older than 30 days, RFCs past comments_close still in draft or review, broken supersede links, duplicate numbers, decisions past their review_by date, and a spot check of a few accepted decisions against the code. Use for a regular review of the decision log, or before a planning round. Read-only until the user says go. Activates on "/decision-log-review", "review th...Votes: 0GitHub stars: 2
- RfcWrite a request for comments (RFC) from a problem statement and run it to a decision: draft, open for comments until comments_close, decide, then hand the outcome to the adr skill, which writes the decision record and links back. Use when a change touches more than one team, is hard to undo or needs comments before a decision. Never overwrites a file. Activates on "/rfc", "write an RFC", "draft an RFC", "request for comments", "propose a change for review", "open the RFC for comments", "close...Votes: 0GitHub stars: 2
- Docs InitSet up a docs tree in the current repository: ask for the spaces, copy the config, a home page per space, the page templates and the build script, fill the front matter (owner, review dates, type) and run the first build. Use when a repository has no docs tree yet, or its docs pages have no owners and review dates. Never overwrites a file. Activates on "/docs-init", "set up docs", "add a docs tree", "docs as code for this repo", "start the documentation".Votes: 0GitHub stars: 2
- Review SweepFind stale docs pages (review date passed, due within 30 days, reviewed: no, no owner or no type), group them by owner, check each page against the system it describes, and update reviewed and review_by only after that check. Use on a schedule, or when pages are past their review date. Reports what changed and what still needs the owner. Never bumps a date without a check. Activates on "/review-sweep", "review the docs", "which docs are stale", "docs review sweep", "fix docs health".Votes: 0GitHub stars: 2
- RunbookWrite a runbook page for one symptom or procedure, from an incident, a chat or the user's notes: Symptom, Checks, Steps, Verify, Roll back or escalate, with owner and review dates, linked from the runbooks index. Use after an incident, or when a procedure exists only in a chat or in one person's notes. One runbook per symptom. Activates on "/runbook", "write a runbook", "turn this incident into a runbook", "document this fix", "add a runbook for".Votes: 0GitHub stars: 2
- Cost BaselineBuild a monthly cost baseline per provider and service from invoices or billing exports (CSV, FOCUS, cloud cost exports), with the period and source of every figure, flags for missing months, one-off charges, spikes and currency changes, written to a docs page. Use when a team needs to know what it spends each month, before a budget, a cost review, a vendor negotiation or a showback. Activates on "/cost-baseline", "cost baseline", "what do we spend", "monthly spend per provider", "build a cos...Votes: 0GitHub stars: 2
- Focus ExportConvert billing data (provider CSV exports, invoice lines, expense exports) to FOCUS, the FinOps Open Cost and Usage Specification, with a column map per format, a validation pass, a reconciliation against the source totals and a list of declared deviations. Use when costs from several providers must sit in one table, when a team wants FOCUS files for a FinOps tool, or before the cost-baseline, showback and unit-costs skills. Activates on "/focus-export", "FOCUS export", "convert billing to F...Votes: 0GitHub stars: 2
- Saas Stack AuditList every SaaS tool the organisation pays for, from invoices, the SSO app list or expense exports, with owner, seats paid and used, overlaps, and a keep, cut or replace proposal per tool, where replace options include open source and agent-built tools with switching cost and risk; the user acts on every proposal. Use when renewals come up, when SaaS spend grows faster than the team, or when nobody can name every tool the company pays for. Activates on "/saas-stack-audit", "SaaS audit", "audi...Votes: 0GitHub stars: 2
- ShowbackAllocate one month of cost per team or service from tags and an allocation file, with shared costs split by a stated rule and unallocated cost as its own line, as a report on a docs page that charges no team. Use when teams should see the cost they cause, when the team wants a number for tag coverage, or before a talk about budgets per team. Activates on "/showback", "cost per team", "showback", "who spends what", "allocate the cloud bill", "split the bill by team".Votes: 0GitHub stars: 2
- Unit CostsCompute cost per unit of work per month (per request, customer, deploy or another unit the team picks), with the cost from the cost baseline, the count from a named metric with its source, and the trend, written to a docs page. Use when the team needs to know whether the systems get cheaper or dearer to run as usage grows, or when it prices a plan or writes a business case. Activates on "/unit-costs", "unit cost", "cost per request", "cost per customer", "cost per deploy", "unit economics".Votes: 0GitHub stars: 2
- Estate AssessmentAssess a repository and its docs, build on the ranked gap list of the sdlc audit, and recommend which modules of the suit to fit, in which order and why, with the first skill, the effort class, the dependencies and an owner per module, written to docs/fit.md. Use when a team or an incoming CTO wants a fitting plan for an existing estate, or wants to know which modules are already fitted. Activates on "/estate-assessment", "which modules do we need", "assess our estate", "fitting plan", "where...Votes: 0GitHub stars: 2
- Add RuleAdd a rule to the deploy gate: install a check that another module ships, or write a new one. Use when the team wants a new mechanical check in the gate, or wants to enable a check that another module ships. Every rule starts in the warn tier, gets a pass fixture and a fail fixture, and moves to the block tier only after a recorded false-positive test. Activates on "/add-rule", "add a gate rule", "gate this", "make the gate check", "install the docs check".Votes: 0GitHub stars: 2
- Gate InitSet up a deploy gate in the current repository: a rules folder, a runner that writes run records, a GitHub Actions workflow whose deploy job waits for the gate, and four starter rules. Use when a repository has no deploy gate yet and the team wants checks to run before every deploy. Copies templates and never overwrites a file. Activates on "/gate-init", "set up the gate", "add a deploy gate", "gate the deploy".Votes: 0GitHub stars: 2
- Run RecordRead the deploy gate's run records and report: the last result, why a deploy was blocked and the shortest fix, open and closed findings, what changed between two runs, and whether the weekly run still happens. Use when the gate blocked a deploy, when someone asks what the gate found, or for a weekly gate status. Can also write a manual run record. Activates on "/run-record", "why did the gate block", "gate status", "what did the gate find", "record a gate run".Votes: 0GitHub stars: 2
- Exit CriteriaSet and track the conditions under which the person handing over a platform leaves: every installed module has a named owner and a backup, every runbook was run by its new owner, the gate and the status page were operated without help for a set period, open decisions are recorded and access has moved, with the state and evidence of each written to docs/handover.md. Use when a handover needs an exit date that follows from evidence, or to check how close the handover is to done. Activates on "/...Votes: 0GitHub stars: 2
- Owner TrainingWrite a training checklist for each installed module of the platform, found by its signal file, that the new owner works through: what to read, what to run, one change made under supervision and how to know the module works, with the progress recorded in docs/handover.md. Use when a platform moves from the person who built it to named owners inside the team, or when a new owner or backup takes over a module. Activates on "/owner-training", "train the new owner", "handover checklist", "onboard...Votes: 0GitHub stars: 2
- Runs Without MePlan and log a test that proves the named owner runs the platform from the docs alone: scenarios such as a deploy, a blocked gate, an incident, a cost spike, a docs review and a new decision, each run by the new owner with no help, with the time taken, the docs used and the gaps found, and every gap turned into a ticket. Use when the person who built a platform is about to leave, or to test whether the docs are enough to operate it. Activates on "/runs-without-me", "does it run without me", "...Votes: 0GitHub stars: 2
- Hiring DebriefRun a hiring debrief with evidence before votes: each interviewer writes evidence and a level per rubric dimension before seeing other scores, the debrief goes through the evidence first, the levels after it, and the decision comes last and is recorded with its reasons and any dissent. Use when a candidate has finished the loop, or when the most senior or most vocal panel member sets the outcome of debriefs. Activates on "/hiring-debrief", "run the debrief", "hiring decision for this candidat...Votes: 0GitHub stars: 2
- Interview LoopDesign the interview loop for one role and write hiring/loop.md: the outcomes the role must deliver, the signals that predict them, the stages, the interviewer role in each stage and the signal each stage collects, with each signal collected once, in one stage. Use when a team opens a role, when interviewers in several stages ask about the same thing, or when interviewers cannot say what their stage is for. Activates on "/interview-loop", "design the interview loop", "set up interviews for th...Votes: 0GitHub stars: 2
- Interview RubricWrite the structured scoring rubric for a role in hiring/rubrics/<role>.json: one dimension per signal in the loop, each with its stage, fixed questions and levels 1 to 4 whose anchors describe observable behaviour, plus the hire bar, all written and frozen before the first interview. Use after the loop is designed, when interviewers score the same answer far apart, or when panel members argue from impressions in the debrief. Activates on "/interview-rubric", "write the rubric", "scoring guid...Votes: 0GitHub stars: 2
- Successor ProfileWrite docs/successor-profile.md, the profile of the person who takes over the platform: the systems they will own, read from the installed modules and the docs in the repository, the skills each system needs, and the interview stage and rubric dimension where a candidate shows each skill. Use when the current platform owner plans a handover, when a team hires the next platform lead, or when nobody can list what the platform owner owns. Activates on "/successor-profile", "successor profile", "...Votes: 0GitHub stars: 2
- Alert RoutesGive every Prometheus alert rule a route label and a runbook_url annotation, route alerts in Alertmanager by that label to one receiver per team and severity with grouping and inhibit rules, write the missing runbooks, and test rules with promtool and routes with amtool. Use when alerts reach the wrong people or nobody, a new team or alert is added, or alerts have no runbook. Activates on "/alert-routes", "route the alerts", "who gets this alert", "add an alert", "alert routing", "alertmanage...Votes: 0GitHub stars: 2
- Dashboards As CodeKeep Grafana dashboards in git as code: write a small JSON spec per dashboard, generate the dashboard JSON with a standard-library build script, let Grafana provision the files read-only, bring UI edits back into the spec, and review every change on the diff. Use when a team adds or changes a dashboard, edited one in the Grafana UI, or has dashboards that exist only in Grafana. Activates on "/dashboards-as-code", "add a dashboard", "change the dashboard", "dashboards as code", "export the das...Votes: 0GitHub stars: 2
- Stack InitSet up an observability stack in the current repository: Alloy, Prometheus, Loki, Grafana and Alertmanager in docker compose, with config files, provisioned data sources and dashboards, retention settings and an .env.example, then start it and check that each component answers. Use when a team has no metrics, logs or alerting yet, or runs them by hand outside git. Never overwrites a file. Activates on "/stack-init", "set up observability", "add monitoring", "set up prometheus and grafana", "o...Votes: 0GitHub stars: 2
- Pressure GradeScore pressure-test run records: compare the decision the system took at each turn with the expected decision, report fold rates per tactic with run counts and 95 percent intervals, mark small samples, report over-refusal on control runs, and score each prediction in red-team/plan.md. Reads only the recorded decisions and never the model's account of its own reasoning. Use after a pressure run, or to compare arms or system versions on the same plan. Activates on "/pressure-grade", "grade the ...Votes: 0GitHub stars: 2
- Pressure PlanWrite the pressure-test plan for an AI feature in red-team/plan.md: the decision the feature makes, a world where the right decision is known in advance, the pressure tactics that apply from an eleven-tactic catalogue, the number of runs and the stop rule, all fixed before the first call. Use when a team wants to know whether its AI feature gives up a right decision, a rule or a task boundary under social pressure, before a red-team run or a release. Activates on "/pressure-plan", "plan a red...Votes: 0GitHub stars: 2
- Pressure RunRun scripted multi-turn pressure against an AI feature in a world where the right decision is known in advance, and write one JSON run record per run to red-team/runs/. The harness sends each turn to the system under test through a command adapter, an HTTP adapter for an OpenAI-compatible chat endpoint, or a stub for tests. Use when red-team/plan.md is frozen and the team is ready to run it, or to rerun the same plan after a change to the feature. Activates on "/pressure-run", "run the red-te...Votes: 0GitHub stars: 2
- IncidentRun an incident from declaration to close: set the severity and the roles (incident lead, comms, operations), keep a timestamped log, post public updates to the incident records and the status page, resolve and close it, and hand over to the postmortem skill. Use when users see errors, slowness or wrong data, when an alert pages on a user-facing symptom, or when someone asks whether this is an incident. Activates on "/incident", "declare an incident", "we have an incident", "is this an incide...Votes: 0GitHub stars: 2
- Nines Per ServicePick an availability target per service from user impact, tier and serial dependencies, check it against the allowed downtime per 30 days, quarter and year and against the product of its dependencies' availabilities, and write it into the service catalogue. Use when a service has no target yet, when a target looks arbitrary, or before a tier change or a customer commitment. Activates on "/nines-per-service", "how many nines", "availability target", "pick an SLO target", "99.9 or 99.99", "allo...Votes: 0GitHub stars: 2
- On CallSet up on-call for the services in the catalogue: the rotation, the escalation policy, the handover checklist and the paging rules (page only on user-facing symptoms, every alert links a runbook), with an audit of the existing alert rules, written to docs/sre/on-call.md. Use when a team starts on-call, when pages wake people for causes users never see, or when nobody can say who answers a page tonight. Activates on "/on-call", "on-call rotation", "set up on-call", "escalation policy", "paging...Votes: 0GitHub stars: 2
- PostmortemWrite a blameless postmortem for one incident: summary, impact in minutes, users and requests, a timeline with a source for every time, contributing factors as mechanisms, what went well and what went poorly, and action items with one owner and a due date each, linked from the incident record. Use when a sev1 or sev2 incident is closed, when an incident used a large share of the error budget, or when the same problem comes back. Activates on "/postmortem", "write the postmortem", "incident re...Votes: 0GitHub stars: 2
- SloDefine a service level objective for one service: the SLI as good events over valid events with exact queries, the target and window, the error budget, multiwindow burn-rate alerts and an error-budget policy, written to a docs page and linked from the service catalogue. Use when a service has a target and no way to measure it, when alerts page on causes users never see, or when releases and reliability work compete for the same time. Activates on "/slo", "define an SLO", "write an SLO", "erro...Votes: 0GitHub stars: 2
- Status PageSet up a static status page built from published records: the service catalogue in services/*.yml and the incident records in incidents/incidents.json, turned into one HTML page and a JSON file by a standard-library script that runs in the deploy job. Use when users need one place to see whether a service works and what happened before, or when a hosted status tool is more than the team needs. Activates on "/status-page", "status page", "set up a status page", "public incident history", "buil...Votes: 0GitHub stars: 2
- Change ReviewReview a change before a person approves it, with a checklist for agent-written code: diff size, scope against the ticket, tests touched, secrets, new dependencies, migrations, generated files and changed tests. Use when a pull request is open, before asking a person to review, or when an agent wrote most of the diff. Activates on "/change-review", "review this PR", "check this diff", "review the agent's change", "is this ready to merge".Votes: 0GitHub stars: 2
- ReleasePrepare a release: a changelog entry drafted from the main line, a rollback plan, the feature flags the release depends on, and the release record with tag, changelog and deploy run. Use before a deploy that users will notice, before tagging a version, or when nobody knows how to undo the last release. Activates on "/release", "prepare the release", "write the changelog", "how do we roll back", "tag a version".Votes: 0GitHub stars: 2
- Sdlc AuditAudit a repository for the stages of a software delivery lifecycle and return the missing ones ranked by the damage each does for what the repository ships to, each with the module or skill that fills it. Use when a team new to the suit wants to know where to start, typically on a repository built fast with coding agents and no process around them. Runs with no other module installed. Read only. Activates on "/sdlc-audit", "audit our lifecycle", "what is missing in this repo", "why does our v...Votes: 0GitHub stars: 2
- Sdlc InitMap the repository's delivery lifecycle and write docs/sdlc.md: a stage table with entry and exit criteria, an owner per stage, the record each stage leaves and the installed module that serves it, with the uncovered stages listed as gaps. Use when a team adopts the suit, or when nobody can say how a change gets from request to production. Activates on "/sdlc-init", "map our lifecycle", "write the sdlc doc", "how do changes ship here", "set up the sdlc".Votes: 0GitHub stars: 2
- Test StrategyDecide what gets tested at which level (unit, integration, end to end, smoke) and define the one command an agent or a person runs before opening a pull request. Writes the test section of docs/sdlc.md. Use when a repository has no tests, tests that CI never runs, or tests nobody trusts. Activates on "/test-strategy", "what should we test", "set up the pre-PR check", "our tests are flaky", "add tests to this repo".Votes: 0GitHub stars: 2
- TicketWrite a ticket from a request, a bug report, a chat or a postmortem action item: problem, testable acceptance criteria, risk, and labels for type, area, priority and status. Also sets up the label scheme in the tracker. Use when work is about to start without a ticket, or when a request is too vague to build. Activates on "/ticket", "write a ticket", "open an issue for", "turn this into a ticket", "set up our labels".Votes: 0GitHub stars: 2