write-spec
Skill15 starsChanged 13 days agoApache-2.0View on GitHub
Synthesize a supplied conversation and established evidence into a behavioral specification, preserving decisions, acceptance, exclusions and unresolved matters. Use for a spec draft, not automatic planning or publication.
28 other projects use a version of this.
Adopted by
Most recently taken up by
- nisarth/claude-skills-storetheir own version, first seen Nov 8, 2026
- dzhng/jevgreptheir own version, first seen Nov 7, 2026
- 0xdeafcafe/skillstheir own version, first seen Nov 6, 2026
- dzhng/skillstheir own version, first seen Nov 4, 2026
- anthod0/skillstheir own version, first seen Nov 2, 2026
- davisbuilds/dojotheir own version, first seen Nov 1, 2026
Used with
Projects with it also use implement-spec-with-codex, close-spec and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dzhngSkillimplement-spec-with-codex
Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.
Also in 4 projects that use this
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 4 projects that use this
wolverin0Skillaudit-decisions
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Also in 4 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 4 projects that use this
LucasMatuszewskiSkillaudit-agents
Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.
Also in 4 projects that use this
antonio-orionusSkillfind-state-machines
Report every implicit state machine in a project, with its states, transitions and flaws.
Also in 3 projects that use this
- +6 more from dzhng
Other versions28 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 28
- anthropics/knowledge-work-plugins★ 35ksame name
- foambubble/foam★ 17ksame name
- dzhng/jevgrep★ 3.2ksame name
- LiberatedPixelCup/Universal-LPC-Spritesheet-Character-Generator★ 1.9ksame name
- dzhng/skills★ 1.5ksame name
- me2resh/apexyard★ 542same name
- AlexPEClub/ai-coding-starter-kit★ 382same name
- dzhng/yap★ 112same name
- dzhng/duet-agent★ 55same name
- smixs/disruptor-skills★ 19same name
18 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository95 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- agent-mailboxSkill
- agent-outputSkill
- ask-gateSkill
- ask-meSkill
- audit-coupled-constantSkill
- budget-checkSkill
- build-prototypeSkill
- caller-optionsSkill
- cold-reviewSkill
- debug-taskSkill
- define-termsSkill
- defuddleSkill
- design-an-interfaceSkill
- diff-recapSkill
- directives-auditSkill
- domain-checkSkill
- double-checkSkill
- extract-signalSkill
- freshness-contractSkill
- github-syncSkill
- handoff-executeSkill
- handoffSkill
- headless-claudeSkill
- headless-codexSkill
- headless-geminiSkill
- headless-grokSkill
- headless-modelsSkill
- headless-update-modelsSkill
- headless-usageSkill
- human-drawSkill
- human-mergeSkill
- human-outputSkill
- human-rewriteSkill
- implement-taskSkill
- improve-codebase-architectureSkill
- insight-adversarialSkill
- insight-anglesSkill
- insight-assessSkill
- insight-critiqueSkill
- insight-cross-examineSkill
- insight-exploreSkill
- insight-premortemSkill
- insight-reference-classSkill
- insight-retroSkill
- insight-root-causeSkill
- insight-skill-gapSkill
- insight-test-assumptionSkill
- insight-value-of-informationSkill
- investigateSkill
- json-canvasSkill
- map-checkSkill
- map-initSkill
- map-maintainSkill
- map-rulesSkill
- map-thisSkill
- monorepo-depsSkill
- multi-agent-modeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
Use only sections that help this reader act.
“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write a specification
Synthesize supplied discussion and established evidence into a standalone spec. Do not restart an interview, conduct open-ended research or invent decisions to appear ready.
Reconcile the input
Identify the problem, audience, current behavior, desired behavior and supplied source boundaries. Read the selected material completely. If it is unavailable or too large to read within scope, state coverage and do not claim complete synthesis. An existing repository spec format governs the output when applicable.
Track later corrections against earlier statements. Where current authority clearly supersedes a choice, state the current choice coherently rather than presenting both as active requirements. Retain the older alternative only when needed to explain a consequential tradeoff. If authority or meaning is disputed, preserve the disagreement as unresolved.
Separate observed facts, agreed requirements and proposed choices. A source file can establish what code does; it cannot silently approve what the product should do. Interview answers, prototype observations and suggested defaults retain their actual status. Preserve negations, numbers, units, scope limits, attribution and uncertainty.
Shape the spec
Use only sections that help this reader act. A typical document includes:
- Problem, audience and present behavior.
- Intended behavior and meaningful examples.
- Acceptance evidence: what observation would distinguish success from failure.
- Established constraints and decisions, with source pointers where useful.
- Non-goals and compatibility requirements.
- Unresolved questions and their consequences for readiness.
Scale detail to the task: refactors need invariants, operations may need actors and exceptions. Invent neither exhaustive stories nor a fixed architecture.
Record testing decisions already made. Do not select new seams or implementation methods by implication. A small exact prototype fragment may be retained when it expresses an established rule more precisely than prose; identify it as modeled evidence and omit irrelevant demo machinery. Paths and snippets belong only where their exact identity helps understand a requirement, rather than as an invented task list.
Reconcile and return
Reconcile consequential inputs as active, superseded, unresolved or explicitly excluded. Retain rejected alternatives affecting interpretation. The spec must stand without these reconciliation notes.
An incomplete conversation can yield a useful spec draft. State exactly which gaps block implementation or approval and which are harmless detail. Producing a spec does not establish approval of its behavior, an executable plan, or permission to implement it. Do not add tracker labels, create tickets, publish or start execution.
Return the draft in the conversation unless the exact save is authorized. For a save, resolve the intended owner and destination, inspect the target and ancestors without following redirects, read current content and retain recovery before a scoped replacement. Preserve unrelated and concurrent edits; an overlapping change needs reconciliation. Existing exact-save authorization needs no second permission question. Missing destination or unsafe ownership yields proposed text with an honest unsaved status.
Report the saved path or text-only disposition, source coverage, material unresolved matters and readiness limits. Source material remains available; synthesis authorizes no cleanup or deletion.
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.

