stock-taking
Skill0 starsChanged 6 months agoMITView on GitHub
Drive Stock-taking Engagement end-to-end (Scope → Audit → Synthesize → Handoff). Gather project context from user up front, dispatch legacy-auditor each phase, persist artifacts under stock-taking/<slug>/, gate phases with user. Use when user building on legacy system, needs understand existing system before project, mentions "stock-taking", "legacy assessment", "inventory", "what do we already have", "existing system", "brownfield", or wants catalogue processes + use-cases before building new.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- plugin-v2/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- plugin-v2/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agents.mdcCursor rule
- agentic-security-reviewSkill
- arc42-baselineSkill
- caveman-commitSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- create-goalSkill
- design-twiceSkill
- discovery-sprintSkill
- domain-contextSkill
- github-project-setupSkill
- grillSkill
- improve-codebase-architectureSkill
- issue-breakdownSkill
- issue-draftSkill
- issue-pr-syncSkill
- new-adrSkill
- new-glossary-entrySkill
- orchestrateSkill
- portfolio-trackSkill
- product-pageSkill
- project-reviewSkill
- project-runSkill
- project-scaffoldingSkill
- quality-assuranceSkill
- quality-metricsSkill
- record-decisionSkill
- review-fixSkill
- roadmap-managementSkill
- sales-cycleSkill
- specorator-designSkill
- specorator-improvementSkill
- specorator-onboardSkill
- tackle-issueSkill
- tdd-cycleSkill
- token-budget-reviewSkill
- tracer-bulletSkill
- ubiquitous-languageSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Always start by reading these (contract you enforcing):
- Distinctive: line 50
No resumable engagements exist → skip to Step 2.
- Very specific: line 79
After Phase 3, dispatch /stock:handoff.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Stock-taking
You conduct Stock-taking Track defined in docs/stock-taking-track.md. Job: sequence phases + gate between — never do auditor work yourself. Each phase runs through legacy-auditor subagent (.claude/agents/legacy-auditor.md).
Shared rules (gating, escalation, constraints common to all conductors): ../_shared/conductor-pattern.md.
This pre-workflow entry. Output = stock-taking-inventory.md feeding /discovery:start or /spec:idea. Skip stock-taking when team starts from scratch with no existing system — recommend /discovery:start (blank page) or /spec:idea (clear brief) instead.
Read first
Always start by reading these (contract you enforcing):
docs/stock-taking-track.md— 3-phase definition + method library.docs/adr/0007-add-stock-taking-track-for-legacy-projects.md— why.memory/constitution.md— Articles II, III, VI, VII apply.- Active
stock-taking/<project>/stock-taking-state.md(if resuming).
The flow you are driving
| # | Phase | Agent | Slash command | Artifact |
| 0 | Bootstrap | — | /stock:start <slug> | stock-taking-state.md |
| 1 | Scope | legacy-auditor | /stock:scope | scope.md |
| 2 | Audit | legacy-auditor | /stock:audit | audit.md |
| 3 | Synthesize | legacy-auditor | /stock:synthesize | synthesis.md |
| H | Handoff | legacy-auditor | /stock:handoff | stock-taking-inventory.md |
Engagement outcomes: complete → inventory produced → /discovery:start or /spec:start + /spec:idea. incomplete → inventory produced with open unknowns → downstream track treats open items as research agenda.
What you do, step by step
Step 1 — Detect resume vs. fresh start
ls stock-taking/ 2>/dev/nullFor each stock-taking/<slug>/stock-taking-state.md with status active, paused, or blocked, list slug | status | current_phase | last_updated. Then batch one AskUserQuestion asking user pick:
- Resume listed engagement (recommended-first by
last_updated). - Start new engagement.
- Skip stock-taking entirely (when user confirms no existing system to inventory).
No resumable engagements exist → skip to Step 2.
Step 2 — Confirm fit (single AskUserQuestion, ≤ 3 questions)
Fresh start → batch into one call:
- Existing system to inventory? —
Yes (run stock-taking)(Recommended) /No existing system — skip to /discovery-sprint or /orchestrate. Second pick → exit skill, recommend appropriate next step. - Project slug — kebab-case, ≤ 6 words, names system or system cluster being inventoried (not feature being built). Good:
crm-legacy-audit,billing-platform-baseline. Bad:new-invoice-feature. - Source material available? — list what they have: code repos, architecture docs, database schemas, runbooks, SMEs, any combination. Seeds
scope.mdsource-material section + calibrates audit depth.
Step 3 — Bootstrap (fresh start only)
Invoke /stock:start <slug>. Creates stock-taking/<slug>/ + stock-taking-state.md with all artifacts pending. Don't edit those files yourself.
Step 4 — Run phases sequentially
Each phase in order:
- Pre-flight — read
stock-taking-state.md, confirm prior phasecomplete(orskippedwith documented compression). - Dispatch slash command (
/stock:scope,/stock:audit,/stock:synthesize). Slash command invokeslegacy-auditor. - Wait for slash command complete + artifact exist.
- Gate with user via single
AskUserQuestion:Continue to <next phase>(Recommended)Pause here— setstatus: pausedinstock-taking-state.md, exit; resume by re-invoking/stock-taking.Re-run <this phase> with feedback(free-text in "Other").- Phase 3 only: also ask whether proceed to
discovery,spec, orboth(populatesrecommended_nextinsynthesis.mdif auditor left asTBD).
Step 5 — Handoff
After Phase 3, dispatch /stock:handoff. legacy-auditor writes stock-taking-inventory.md. Then:
recommended_next: discovery→ recommend/discovery:start <sprint-slug>.recommended_next: spec→ recommend/spec:start <feature-slug> [<AREA>]followed by/spec:idea.recommended_next: both→ recommend both paths with note on which parts of system scope feed into each.- Confirm with user whether chain into
/discovery-sprintor/orchestrateimmediately or pause. - Set
stock-taking-state.mdstatus: complete.
Constraints (stock-taking-specific)
Generic conductor constraints + escalation pattern: ../_shared/conductor-pattern.md. Specifics for this skill:
- Never open
specs/<feature>/ordiscovery/<sprint>/from inside this skill — that happens after handoff via/spec:startor/discovery:start. - Never recommend stock-taking when the user confirms no existing system to inventory.
References
docs/stock-taking-track.md— full methodology.docs/adr/0007-add-stock-taking-track-for-legacy-projects.md.docs/sink.md—stock-taking/sink layout..claude/agents/legacy-auditor.md— agent this skill dispatches.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.