All authors
Claude Skills by intent-driven-ai
github.com/intent-driven-ai111 skills0 installs0 views
- Author Encrypted EvalsGenerate testable verification evaluations from spec inputs (product-spec behaviors, verification scenarios, epic success and failure conditions, LLD exit-gate text), encrypt the resulting YAML with AES-256-CBC + PBKDF2, delete plaintext, and write a manifest.json. Single common skill for the evals-engineer agent.Votes: 0GitHub stars: 3
- Author Failure RecoveryDraft, for each feature of a slice, its entry in the slice's hidden file — one recovery for each "Fails if" line of the feature's ICE and of its capability's ICE (when it shows, the way back, and who fixes it, "the builder can fix this alone" or "a person must decide"), by standards/rules/expectation-generation.md, "A feature's recovery". It reads the lines its agent put in short-term memory (write_hidden_file.py lines), drafts only the entries that are not kept, and says when one of the two ...Votes: 0GitHub stars: 3
- Author Fix DesignGiven a completed rca.yaml, design a fix with at least one alternative considered and rejection reason, affected-files map with change specifications, and a self-sufficient execution plan. Writes design.yaml.Votes: 0GitHub stars: 3
- Author Implementation PlanCreate a plan.yaml artifact — execution order of features as vertical slices with scope items, exit gates, and scenario gatesVotes: 0GitHub stars: 3
- Author Intent PageWrite a business intent's page in the product model from its draft — a new page, or a rewrite of one that is there. The draft starts as the intent-draft.json that author-business-intent writes in one-intent mode, and a caller may add the optional fields rules, serves, identified_by and touches. The page holds what the draft holds, and this skill drafts nothing. Its script writes every part in one fixed order (title, outcome, why, asked by, proof it is met, must not, rules, serves, identified ...Votes: 0GitHub stars: 3
- Author Knowledge BriefWrite the brief a loop shows the person when it must reach them — what we understood, what we built, and where the gaps are, each with its context and our proposed answer — the way you would brief someone who can help close the piece. A few themed gaps (at most seven), the knowledge pages waiting for approval with our recommendation, and a pointer to the prototype notes. Never a questionnaire. Used by the knowledge-builder agent in the loop's knowledge step (Shared Loop Run, R5c).Votes: 0GitHub stars: 3
- Author Knowledge PageDraft one knowledge page for a topic a loop found missing from memory — something no screen shows and research can answer (a speed bar for a kind of product, the rules that apply to a kind of record, the usual roles in a kind of team) — researched with its sources. One page answers every question of its topic. Marks the page for the project's memory when it is a fact about the product or its team, not about one loop. Draft only — the knowledge-builder agent raises the page through the memory ...Votes: 0GitHub stars: 3
- Author LearningsRead a delivered unit''s real outcomes — the measure lens (baseline/target/realized), the validate verdicts and fix reports, the run lens (production actuals), and the delivered epic/slice status — against the current product model, and author the MEANING updates the delivery taught — a refined capability/feature one_line, a raised nfr_needs level (monotonic-up), an earned status promotion, the grounding-doc sections the learning changed, and a new append-only decision per material learning. ...Votes: 0GitHub stars: 3
- Author LldCreate a tech.yaml artifact with project structure, libraries, data model, components, design decisions, and feature mapping from features and architecture specificationsVotes: 0GitHub stars: 3
- Author Marketing LensAuthor a shaped slice's marketing lens as an MD grounding doc — discoverability (SEO + AEO + GEO), accessibility (moved here from the profile), and marketing analytics — from the slice's hub (its features' grounding docs + the spine profile) and KB grounding. An internal tool behind auth says "SEO/AEO/GEO not applicable" plainly, with the reason. Under direct-model-write (ADR 026) it writes the slice's marketing.md STRAIGHT to the live model (a re-derive) and emits any material decision plus ...Votes: 0GitHub stars: 3
- Author Measure LensAuthor a shaped slice's measure lens as an MD grounding doc — the delivery-measurement focus, a table of metrics (metric / baseline / target / proof, triangle-primary speed/tokens/cognition), and what is out of scope — from the slice's hub (its features' grounding docs + the spine profile). Every metric is concrete (a baseline, a target, a proof), never a vague claim. Writes measure.md STRAIGHT to the live model (per-node doc only, conforming to the Measure lens template) and emits the shared...Votes: 0GitHub stars: 3
- Author Plan ChangesTurn one instruction a person gives in an /update-plan session, in their own words, into the list entries it means for the plan — a status set, an item added (an issue that exists, or a new one), moved, renamed, given a new text or a new kind, a new feature found while the plan is in progress, or the plan's own Status or Direction — read against the plan file, the issues as the tracker holds them now and the list so far. Asks a question instead of guessing when the words fit two readings or n...Votes: 0GitHub stars: 3
- Author Plan FileCreate, update, or check the plan for one issue — what gets done, in what order, and why, never how — written to the issue's STM as specs/plan.md in the canonical plan format. Called by an agent after it has gathered the plan context (the issue, its parent, its child issues, any plan already on disk). Use before work starts (create), whenever work finishes, starts, or the order changes (update), and before an issue is called done (check). The check runs a script, so a play's done check can re...Votes: 0GitHub stars: 3
- Author Play IceAuthor a structured intent.yaml file (the ICE clean triple) from interview material. Takes an extracted interview digest (goal, constraints, failure conditions) and produces a well-formed intent.yaml conforming to the Garura intent schema. Scenarios and recovery are NOT written here — they are generated into the play's expectation.yaml by draft-play-expectation.Votes: 0GitHub stars: 3
- Author Product OntologyBuild or extend the product ontology — the agreed, human-readable map of the kinds of things a product is made of, what each holds, how they connect, and what must always be true — one kind at a time, with the person. Follows the classic seven-step method (scope by questions, reuse, terms, kinds, properties, rules, instances) and writes the ontology in the canonical format, checked by a script. Run only by the edit-ontology play, one stage at a time, when the product model needs a new kind of...Votes: 0GitHub stars: 3
- Author Quality LensAuthor a shaped slice's quality lens as an MD grounding doc — a short statement of what "good" means for the slice plus a table of checkable gates (dimension / bar / how checked) — from the slice's hub (its features' grounding docs + the spine profile's NFR gates). Every gate is grounded (a profile gate that applies or a feature's rule made checkable) and concrete, never a vague adjective. Under direct-model-write (ADR 026) it writes ONLY the per-node lens docs (`quality.md` conforming to the...Votes: 0GitHub stars: 3
- Author RcaTrace a reported defect from symptom to specific root cause — the file, the logic, and why it is wrong — and author rca.yaml plus resolution-trace.yaml (when LTM context provided). Used by tech-designer in the fix-it play.Votes: 0GitHub stars: 3
- Author Run LensAuthor a shaped slice''s run lens — write the narrative grounding doc (run.md) straight to the LIVE model, and emit the machine-readable per-environment definition (run.yaml) plus any decision as STRUCTURED MANIFEST DATA for the play''s keyed persist to write. How the slice ships and operates: the slice-level design (rollout, migrations, CI/CD, TCO) written once, and ONE environment defined per call (local for /release-epic, or a cloud environment for /release-increment — provider, region, co...Votes: 0GitHub stars: 3
- Author Slice BriefWrite the opening of a /shape-slice brief — the early brief (the questions asked before the slice is shaped) or the confirmation brief (the slice shown for the person's yes) — in two or three plain sentences that say what the person decides and what happens with the reply, by the rule for asking a person, or by the play's floor when gather.json has rule_missing. Writes the opening only; the play's render_brief.py builds the rest of the brief from the run's records. Generative artifact product...Votes: 0GitHub stars: 3
- Author Slice EvalWrite the eval of each ready slice of a business intent's plan, for /shape-eval — one story file for each story of the slice's epic (eval.<feature-id>.feature.md, Markdown with Gherkin, its Feature is the story) with a scenario for each goal and each expectation of the story and, for each failure condition of the story's feature in the slice's hidden file, a scenario that shows it does not happen; and one slice file (eval.<slice-id>.md) that lists the stories in build order with the surface k...Votes: 0GitHub stars: 3
- Author SliceChoose the one slice that shows a business intent is served, for /shape-slice — the one surface and the persona who tests it there (the tester), the features from any capability in build order with why_this_order, what is left out, and the needs list of the model (fills.json — the new parts, the updates to parts that exist, the thin parts). Writes slice.json and fills.json, or no-slice.json with its reason when no surface can be tested end to end. Reuse mode writes reuse.json (pull_in, push_o...Votes: 0GitHub stars: 3
- Author Steelman EvalsAuthor /build-epic''s steelman evals for ONE epic — adversarial refutation checks the independent verifier runs against a build that claims "done". Reads the epic''s acceptance criteria, user_check, the feature ICE (failures especially), the quality lens gates, and the build plan''s test pieces; writes refutation-style evals — each one a concrete attempt to PROVE THE CLAIM FALSE (probe an edge, violate a constraint, exercise a failure condition, game-check a test) with a binary pass rule. Com...Votes: 0GitHub stars: 3
- Author Technical ApproachCreate an architecture.yaml artifact with technology selections, NFRs, platforms, integrations, and agentic PCAM design from a features specificationVotes: 0GitHub stars: 3
- Author Ux LensAuthor a shaped slice's UX lens as an MD grounding doc — the screens (with low-fidelity layouts), the flows that EXPAND the slice's journey records onto those screens (one flow per journey, never an invented one), the states each holds, and the product's visual core (the semantic state vocabulary, its tone map, and the design-system reference the look comes from — never a chosen palette or typography) — from the slice's hub (its features' grounding docs + the spine profile + the slice's perso...Votes: 0GitHub stars: 3
- Author Validation ChecksAuthor /validate-epic''s check manifest for one EPIC — the toolchain plan the run_checks orchestrator executes. Detects the product''s stack(s) from the slice''s architecture lens tech picks plus the repository''s own manifests (package.json, pom.xml, *.csproj, migrations), then resolves each stack to its tooling — build, test runner, linter, scanner, dependency audit — as KB-GROUNDED choices via find-architecture-learnings; anything the KB does not cover becomes a recorded KB-learning-gap pr...Votes: 0GitHub stars: 3
- Author Verification ScenariosCreate a scenarios.yaml artifact with grouped scenarios, feature back-links, feature gates, and coverage summary from a features specificationVotes: 0GitHub stars: 3
- Author Work ItemsWrite, for each slice of a business intent's plan, the epic's title (what a person can see the product do, not how it is built) and one story for each ready feature — its title, its scope of work (goals, limits, expectations) and its Context guidance (what to read, what never to read, the persona, what is in and what is out) — in its own words, from skill-input.json and the clean copies of the feature's ICE and its capability's ICE that the play's gather_plan.py wrote — the only files it read...Votes: 0GitHub stars: 3
- Check Generated TestsExecute generated tests against the current codebase using the detected TEST_HARNESS and report pass/fail per test. Context-isolated — consumed ONLY by a test-running agent that receives no extraction context. Reports pass/fail plus stderr; does not interpret failures. This is the baseline-green verification gate for /decode (C25).Votes: 0GitHub stars: 3
- Check Pr QualityDiff-bounded single-pass quality evaluation for PR review. Classifies every changed path by ARTIFACT TYPE first (runtime code / deployable config / tests / docs-planning / garura prose / ProductOS model / STM evidence / wireframes — pure globs, first match wins), then evaluates standard-ID checks against the diff using mechanical match rules from the PR severity taxonomy — grep-based rules fire only on runtime-code/deployable-config/tests (a keyword in prose is not a security defect, #438); p...Votes: 0GitHub stars: 3
- Check Quality GatesExecute a quality lens''s binding cards — the machine sibling quality-gates.yaml — against a project and emit one verdict per gate. Runs every machine-owned card''s command through the project''s own tools (linters, tests, type checks, coverage, custom check scripts), reads declared measures against thresholds, and normalizes outcomes to pass | fail | error | missing-tool | human. A card whose demanded tooling is absent is a missing-tool FINDING the build loop consumes as provisioning work — ...Votes: 0GitHub stars: 3
- Check QualityQuality assessment framework using 11 parallel explore subagents across code, testing, security, architecture, documentation, operations, frontend, backend, data, performance, and tech-debt governance. Reads KB quality standards calibrated by the project's Quality Profile (quality-standards.yaml). Produces scored assessments with HTML spider chart, JSON, and Markdown reports. Use when assessing project quality, running quality audits, checking production readiness, or evaluating tech debt gov...Votes: 0GitHub stars: 3
- Commit FilesStage files and create one or more commits in a single passVotes: 0GitHub stars: 3
- Cut BranchCreate branch, push to origin, optionally use worktree for dirty treesVotes: 0GitHub stars: 3
- Deploy Cloud EnvironmentDeploy a delivered increment to ONE resolved cloud environment exactly as the slice's run lens (run.yaml) declares it — run the environment's declared deploy command honoring its provider, region, compute, services, and networking; read secrets only from the declared secrets-manager binding (never print or store them); then prove the increment answers with an independent reachability/health check and capture a deploy record (environment, what ran, address, health proof, secrets source). On fa...Votes: 0GitHub stars: 3
- Deploy Local EnvironmentBring one epic''s increment up LIVE on the slice''s LOCAL environment so a human can walk it — the deploy half of /release-epic''s HITL gate. Reads the slice''s structured run.yaml for the local environment''s declared bring-up (its `local.run` command and any seed) and the repository, brings the increment up there, verifies it is actually reachable, and writes a deploy record: environment, target, the reachable address, any seeded test credentials, and how to tear it down. NEVER stands up a ...Votes: 0GitHub stars: 3
- Derive Blast RadiusGiven a change surface (file list) and a dependency graph, compute directly and transitively impacted tests, identify coverage gaps in the change surface, and emit blast-radius.yaml. Used by test-engineer.Votes: 0GitHub stars: 3
- Enrich Capability IceFind the capabilities a prototype's screens show (find mode, ADR 043), or detail one capability — already in the model, seeded from the person's recorded answers, or read off the screens — promote its capability.md from the directional stage to the detailed stage (benefit hypothesis, boundary, guiding rules, features), author a detailed feature.md grounding doc for each feature it identifies, set the capability's structured nfr_needs + compliance_needs, and emit the implied per-dimension leve...Votes: 0GitHub stars: 3
- Enrich GroundingWrite on the pages of the product-model parts a slice needs, for /shape-slice, from the person's answers and the assumptions, keeping every section and line a page had — bring each domain, capability or feature page the slice moves or uses up to the current grounding rules, in place; write one new feature page under a capability that exists, without re-detailing the capability; thin-ICE mode writes the minimum ICE (Goal, Limit, Fails if, Context, Checked by) for a part that has none; fix mode...Votes: 0GitHub stars: 3
- Enrich Quality ProfileStage 2 skill of /shape-architecture-lens. Reads the /specify quality profile, refines targets against architectural reality (inventory constraints, project-profile pins, epic constraints), and writes the refined quality profile to architecture/ with a delta log of every adjustment. The refined QP describes the NFRs physical must deliver; it does NOT name mechanisms.Votes: 0GitHub stars: 3
- Find Answers In SourcesFor each group of a loop's open questions, look in the loop's own sources again — for a prototype, every captured view, every journey step and the page itself (its text, labels, sample data and script) — and answer with a quote and the place it was found. Marks each group answered, partly answered (naming the part still missing) or not shown, and for not shown says whether the source should show it (a gap in the prototype) or no screen could (knowledge or the person). Used by the knowledge-bu...Votes: 0GitHub stars: 3
- Find Architecture LearningsSearch the empirical Knowledge Base for the best-fit architecture and technology learnings given a product's conditions. Use during context-building in the realize lenses (/shape-architecture-lens, /shape-run-lens, /shape-ux-lens, /shape-agentic-lens) when you need to know what worked before for a product in this situation — its stage, scale, persistence, and monetization. Reads the architecture/ and technology/ shelves (the condition-matched, "what works for us" engine), distinct from find-w...Votes: 0GitHub stars: 3
- Find Matching IssuesMap change groups to existing open issues with confidence scoring. Use when you have grouped file changes and need to determine which issue each group belongs to before committing.Votes: 0GitHub stars: 3
- Find Model GapsFind the gaps in the product model — the nodes not yet linked (a capability with no domain, a feature with no capability, a node that serves no business intent), the same thing written twice, the work still missing (a capability with no features, an intent no capability serves) and the screens of a prototype no node covers — and say, for each, the link to make or the play that does the missing work. Every kind is written on its own (ADR 043), so the model holds loose nodes until they are link...Votes: 0GitHub stars: 3
- Find Slice GapsList each thing a slice needs that neither the product model nor memory answers, for /shape-slice, and write each as one question by the rule for asking a person — id, topic, question (one thing), why, examples from several domains, blocking, assume, and settled with its basis when the context answers it after all. The surface and the tester are never a question (author-slice proposes them). Rewrite mode rewrites only the questions that record_questions.py proposals refuses. Reads only what i...Votes: 0GitHub stars: 3
- Find Work PlacementSearch the product knowledge base for where a piece of work belongs — its domain, capability, and feature — by reasoning over the domain shelves its agent puts in short-term memory. Runs the inference sandwich (list the domains, reason to the domain, read that shelf, reason to the capability/feature) and emits a lightweight routing-result with the decision and why. Placement only — it does not evaluate product-profile conditions (that is selection, not placement). Use whenever a play or agent...Votes: 0GitHub stars: 3
- Judge GroundingGrade ONE product-model grounding doc (a domain.md, capability.md, feature.md or epic) for whether a stranger could understand it, and write the verdict JSON. It holds the grounding judge's rubric (five criteria), its prompt and its verdict shape — the one source for them (ADR 039 §7). It runs inside an isolated, clean-context judge sub-agent that is handed only the doc, its parent doc when there is one, and the kind's per-section guidance (and, in a fix round, the last verdict's failures); i...Votes: 0GitHub stars: 3
- Judge Loop ResultCheck a finished loop's result against what the loop promised, and give a pass or reject verdict with a reason for every criterion. It holds the loop checker's rules, its prompt and its verdict shape — the one source for them, used by both kinds of checker (a sub-agent on a different model, or a different coding agent such as Codex). The checker is handed only a bundle of the loop's outputs (the change it made, its plays' review records, the answers and where each came from, the decision-trac...Votes: 0GitHub stars: 3
- Judge Validation ResultsCompose /validate-epic''s findings from CAPTURED results only — the judgment half of the finder''s job. Reads the normalized check results (results/*.json + summary.json from run_checks) and the gates/benchmark map (gates-map.json from check_gates), and writes findings.yaml — one entry per real problem, each carrying its mechanical citation (the failing check id, the rule that fired, the gate or benchmark) and its location (file:line where the tool named one, else the raw log path). Adds judg...Votes: 0GitHub stars: 3
- Link Model GapsClose the gaps in the product model that the model itself can close, from the gaps.json find-model-gaps wrote — attribute each loose node to its parent (a capability to its domain, a feature to its capability), moving a holding-folder page under its parent unchanged; link nodes to the business intents they serve on both sides (the spine and the intent page's Touches list); and merge two nodes agreed to be the same thing. It writes no new page and no intent content, and deletes only a merged d...Votes: 0GitHub stars: 3
- Link Model PartPut a domain, capability or feature into the product model's spine — the model's index of every part — after its page is written, for a part found during other work (#979). A new part gets its spine entry (its parent, intents, one-line, page, issue, status proposed, marked to be deepened); an existing one gets its one-line replaced, its intents added or its issue named; a slice that exists gets features added to it, at its end or after a named feature (#931 — a slice itself is shaped only by ...Votes: 0GitHub stars: 3