Claude Skills by chan4lk

github.com/chan4lk

37 skillsA× 36B× 10 installs59 views

ArchiveAMove a completed change to .specclaw/changes/archive/ under its existing name. Closes the GitHub Issue (if sync is enabled) and optionally creates a git tag. Use after a change is merged — the PR is complete and the change should leave the active list.ai-agentsazuregitVotes: 0GitHub stars: 13
Auth AzdoAInteractive setup for Azure DevOps authentication. Prompts for organization, project, and repo, validates a Personal Access Token, and saves credentials to gitignored .specclaw/.env. Run once per project before /specclaw:pr-azdo.ai-agentsshellazureVotes: 0GitHub stars: 13
Auth JiraAInteractive setup for Jira authentication. Prompts for domain, email, project key, and issue type, validates an Atlassian API token, and saves credentials. Run once per project before /specclaw:issue.ai-agentsshellgitVotes: 0GitHub stars: 13
Author SpecAInteractively co-author spec.md for an approved proposal via the spec-author subagent. The agent walks the user through the spec template section by section, applying named brainstorming techniques (5 Whys, Jobs-to-be-Done, Inversion, Pre-mortem, MoSCoW) and challenging vague requirements. Use when you want a high-quality, dialogue-driven spec instead of the single-shot one /specclaw:plan produces by default. Standalone alternative to /specclaw:plan --author-spec.ai-agentsazuregitVotes: 0GitHub stars: 13
AutoARun the propose → plan → build → verify lifecycle autonomously across the queue of active changes. Advanced — requires automation config in config.yaml. Use when you want specclaw to advance every change to its next phase without prompting; do not use for a single targeted change (use the specific verb instead).ai-agentsVotes: 0GitHub stars: 13
Azdo IssueACreate or update an Azure Boards Work Item that mirrors this proposal. Targets Azure DevOps Boards (Features / User Stories / Tasks / Bugs / Epics) using the credentials from /specclaw:auth-azdo. Mirrors /specclaw:issue (Jira) and the GitHub Issues sync but for ADO Boards. Requires `azdo.boards.sync: true` in config.yaml.ai-agentsbashazureVotes: 0GitHub stars: 13
Skills DirectorySkills Directory Look up any of 103,619 scanned skills — grade, score, and every finding. Free.Check a skill
BuildAImplement planned tasks by executing them wave-by-wave, committing each, and logging errors and learnings. Reads tasks.md and drives the build loop. The longest-running phase of the specclaw lifecycle. Run after /specclaw:plan has produced spec.md, design.md, and tasks.md.ai-agentsgobashVotes: 0GitHub stars: 13
ContextAManage the project's living context document (.specclaw/context.md). View, add, or edit project-level rules, patterns, coding style, and architecture decisions that all lifecycle skills load automatically. Use show to view, add to append a rule, edit to rewrite a section, reset to restore from template.ai-agentsgitVotes: 0GitHub stars: 13
InitAInitialize specclaw in this project. Creates the .specclaw/ directory, generates config.yaml from the template, and sets up the project dashboard. Run once per project before any other specclaw command.ai-agentsgitVotes: 0GitHub stars: 13
IssueACreate a Jira issue for a proposed change. Mirrors GitHub Issues sync but for Jira-based teams. Builds the issue summary and description from proposal.md and spec.md. Requires credentials from /specclaw:auth-jira. Idempotent — warns if a Jira issue already exists for this change.ai-agentsgitapiVotes: 0GitHub stars: 13
LearnARecord a build learning — a spec gap, design miss, recurring pattern, or insight discovered during implementation. Appends to .specclaw/changes/<change>/learnings.md. Use mid-build to capture knowledge before it's lost; do not use for routine progress updates.ai-agentsgobashVotes: 0GitHub stars: 13
LoopAAutonomously iterate build→verify→review until every gate is green or a guardrail halts. Drives the specclaw-loop controller — evaluate gates, reflect, fix the smallest diff, re-verify the whole change, and repeat. Use when asked to loop, iterate until done, or keep fixing until tests pass / verify passes / review is clean. Default-on around /specclaw:build and /specclaw:verify.ai-agentsgobashVotes: 0GitHub stars: 13
PatternsAInspect the cross-change pattern registry. Track recurring errors and learnings across changes; promote patterns with 3+ occurrences to prevention rules. Use to see what keeps happening before planning a new change.ai-agentsbashVotes: 0GitHub stars: 13
PlanAGenerate spec, design, and ordered task list for an approved proposal. Reads proposal.md, analyzes the codebase, then writes spec.md, design.md, and tasks.md. Run after /specclaw:propose has been approved, before /specclaw:build.ai-agentsgobashVotes: 0GitHub stars: 13
Pr AzdoACreate an Azure DevOps pull request for a verified change. Mirrors /specclaw:pr but targets ADO Repos via REST API instead of GitHub. Requires credentials from /specclaw:auth-azdo. Use when the project uses Azure DevOps instead of GitHub.ai-agentsazuregitVotes: 0GitHub stars: 13
PrACreate a GitHub pull request for a verified change. Reads verify-report.md, opens a PR with title from proposal and body from spec, enforces the configured test policy. Requires the gh CLI authenticated. Run after /specclaw:verify produces a verify-report.md. For Azure DevOps PRs, use /specclaw:pr-azdo instead.ai-agentsbashazureVotes: 0GitHub stars: 13
ProposeADraft a new change proposal. INVOKE IMMEDIATELY whenever the user mentions a proposal, feature idea, change request, new initiative, or anything they want to add/build/implement — do NOT gather details conversationally first. The skill itself will ask for any missing information after invocation. Creates .specclaw/changes/<name>/proposal.md with problem statement, solution, scope, impact, and open questions. When party.enabled is set, also runs the adversarial review panel over the draft — as...ai-agentsrustgoVotes: 0GitHub stars: 13
RenumberABackfill ordinal number prefixes onto existing change folders — renames .specclaw/changes/<name>/ to <NNN>-<name> in creation-date order, across active and archived changes alike. Use when /specclaw:status or /specclaw:propose reports unnumbered changes, when `ls .specclaw/changes/` reads alphabetically instead of chronologically, or when the user asks to number, renumber, or reorder change folders. Shows a dry-run plan and renames nothing without explicit confirmation.ai-agentsVotes: 0GitHub stars: 13
StatusAShow the project's specclaw dashboard — active changes, completed changes, pending proposals, blocked work. Reads .specclaw/STATUS.md. Read-only; does not modify state.ai-agentsVotes: 0GitHub stars: 13
VerifyAValidate that the implementation satisfies the spec's acceptance criteria. Runs the configured test/lint/build commands, evaluates against spec.md, and produces verify-report.md. Required before /specclaw:pr. Run after all tasks in /specclaw:build are complete.ai-agentsgobashVotes: 0GitHub stars: 13
Bf AnalyzeAAnalyze an existing (possibly legacy) codebase and write a grounded `.specclaw/analysis/codebase-report.md` covering tech stack, dependencies, architecture, domain, and risks. Works on any language or stack — Node, .NET, Java, Go, Rust, Python, Delphi/Object Pascal, or none of the above — not just Node/.NET. Read-only: no TTY or credential prompts, no lifecycle gate. Use when onboarding to an unfamiliar or legacy repo, or before proposing a change in one.ai-agentspythonrustVotes: 0GitHub stars: 13
Bf ArchitectureAProduce a C4-model architecture view (L1 System Context → L2 Containers → L3 Components → L4 Code, L4 only where warranted) of an existing/legacy codebase, with a Mermaid flowchart plus grounded prose per level, written to `.specclaw/analysis/architecture.md`. Works on any language or stack — Node, .NET, Java, Go, Rust, Python, Delphi/Object Pascal, or none of the above. Read-only: no TTY or credential prompts, no lifecycle gate. Use when you need a visual map of how a codebase's pieces conne...ai-agentspythonrustVotes: 0GitHub stars: 13
Bf BaselineADesign, generate, and record the golden-master harness that proves a rebuild behaves identically to the legacy app it replaces. Default mode ranks seams (pure function / stateful service / HTTP-API / data boundary / UI-excluded), declares each seam's capture layer, audits every seam for non-determinism (clocks, identity values, unstable ordering), and derives scenarios from domain-model.md's numbered business rules — writing .specclaw/baseline/seams.md and scenarios.md. Ends by asking the hum...ai-agentsrustgoVotes: 0GitHub stars: 13
Bf BlueprintASynthesize the decisions a brownfield rebuild has already made — decisions.md, module-map.md, architecture.md, rebuild-backlog.md — into .specclaw/analysis/target-architecture.md, the target-side counterpart to architecture.md's legacy view. Produces Mermaid C4 diagrams (one Context, one Container, one Component per MOD-###), a legacy-to-target mapping table in which every row cites the SQ/CQ decision that sanctions it, and stack/persistence/hosting/auth sections where every claim carries its...ai-agentsrustgoVotes: 0GitHub stars: 13
Bf BootstrapACreate the target application foundation in the NEW (rebuild) repo, before any backlog item is developed — the missing stage between "the rebuild backlog exists" and "/specclaw:propose BL-###". Consumes the architecture the rebuild already decided (decisions.md's SQ/CQ answers plus any accepted ADR in this repo) and scaffolds the skeleton for it: app shell, routing shell, API client, solution/project layout, ORM and database connectivity, dependency injection, environment/config structure, CO...ai-agentsrustgoVotes: 0GitHub stars: 13
Bf ClarifyATurn the extraction signals scattered through .specclaw/analysis/*.md (Inference:, Mechanical:, Named Gaps, hedging language, cross-doc conflicts, unexercised code paths) into a numbered, human-answerable question set — .specclaw/analysis/clarifications.md — classified as DECISION, DATA, SCOPE, DEFECT, MECHANICAL, TARGET-GAP, or CONFLICT, each with options and a proposed default. Also asks the standard bank of shaping questions every rebuild needs (target platform, database, auth, hosting, .....ai-agentsrustgoVotes: 0GitHub stars: 13
Bf DomainAProduce a domain and functional-spec view of an existing/legacy codebase — business entities, relationships, rules, and enumerations (domain-model.md) plus capabilities, workflows, UI inventory, and named gaps (functional-spec.md) — grounded in parsed forms (.dfm/.xaml), type/const declarations, and validation-routine candidates. Also proposes the module map (module-map.md): evidence-grouped MOD-### migration units — owned vs referenced-but-not-owned entities, rules, services, screens, and in...ai-agentsbashVotes: 0GitHub stars: 13
Bf E2eAAutomatically detects the target application's platform (Web/Desktop/Mobile/Hybrid/Embedded) and stack, dynamically selects the most effective E2E testing framework for it with a stated justification, and generates a Page Object Model plus a runnable E2E test script that asserts the application's own observable business behaviour — derived independently from the application's real features/flows and any flow description you give it. No fixed platform/language/framework list, and no dependency...ai-agentsgobashVotes: 0GitHub stars: 13
Bf QualityBMeasure the code quality of an existing/legacy codebase and write a machine-readable .specclaw/analysis/quality.json plus a client-curatable quality-report.md — per-module rollups of cyclomatic complexity, function length, duplication and file length, each classified against configurable thresholds, with every metric that could not be computed recorded as NOT-MEASURED and a machine-readable reason (tool_missing / language_unsupported / parse_error) rather than estimated. Hotspots are register...ai-agentsgobashVotes: 0GitHub stars: 13
Bf Rebuild PlanARead the five .specclaw/analysis/*.md documents (codebase-report, architecture, domain-model, functional-spec, module-map) — plus, when present, decisions.md, clarifications.md, and .specclaw/baseline/manifest.json/scenarios.md — and write or refresh an ordered .specclaw/analysis/rebuild-backlog.md: the application decomposed into individually-proposable features, grouped under the MOD-### migration modules from module-map.md in the map's own dependency order (foundations first) and sequenced...ai-agentsrustgoVotes: 0GitHub stars: 13
Bf ReplayAGolden-master comparison — replays captured legacy fixtures (.specclaw/baseline/manifest.json + fixtures/) against the new app's own behaviour and reports MATCH/DIVERGES/ERROR per fixture, with four mutually exclusive selection scopes (a change's BL item, a single `--item BL-###` backlog item, a `--module MOD-###` module, or the whole corpus) so a large legacy system can be accepted one item or one module at a time, classifying every divergence in bash as behavioural (the rebuild decided diff...ai-agentsrustgoVotes: 0GitHub stars: 13
Bf StatusAShow where a brownfield rebuild actually stands — one row per bf-* phase (analyze, architecture, domain, clarify, ui, baseline, rebuild-plan, blueprint, bootstrap, replay), what each produced, every open item holding a phase back, and the single next command to run. The bf-* counterpart to /specclaw:status, which reports the propose→plan→build→verify lifecycle and says nothing about the rebuild workstream. Read-only and deterministic — spawns no agent, reads no source code, and writes nothing...ai-agentsgobashVotes: 0GitHub stars: 13
Bf UiAOptional UI-fidelity workstream for a rebuild — extract the legacy app's UI structure and visual theme from its source (.specclaw/ui/ui-inventory.md with a permanent SCR-### per screen, design-tokens.json with permanent TK- token groups, and screenshot-checklist.md as a human capture work order), then record the human-captured screenshots into a hashed ui-manifest.json (--record), then generate a per-change human sign-off table in the new repo (--checklist <change-name>). Stack-agnostic — the...ai-agentsgobashVotes: 0GitHub stars: 13
SpecclawARun the SpecClaw spec-driven lifecycle in this repository when a request needs proposal, planning, build, verification, PR, or lifecycle-status work.ai-agentsbashgitVotes: 0GitHub stars: 13
DebugAUse when a bug, test failure, build failure, or unexpected behaviour is reported or observed, before proposing any fix.ai-agentsgobashVotes: 0GitHub stars: 13
Using SpecclawAUse when a session starts in a repo that has a .specclaw/ directory — establishes how specclaw verbs are chosen.ai-agentsgoVotes: 0GitHub stars: 13
Bf PrototypeAMandatory design-approval stage for a brownfield rebuild that decided SQ-013 REINTERPRET; inert otherwise. Briefs a redesigned prototype and gates the new repo on the client's approval (PROTOTYPE: READY). Run after /specclaw:bf-blueprint, when SQ-013 is REINTERPRET.ai-agentsbashfrontendVotes: 0GitHub stars: 13