to-spec
Skill3 starsChanged 2 months agoMITView on GitHub
Before reading relative links, run cd '<loaded-skill-directory>' && pwd -P with this loaded file's directory to obtain the physical base, then resolve links against that printed directory. Resolve the source symlink before applying ... Read linked files even when their skills are absent from the discovery list. Produce a new or updated Spec from information already established in the conversation, repository, or a supplied Scratchpad. Do not conduct a requirements interview, invent decisions, or treat the Spec as an implementation…
194 other projects use a version of this, 3 of them edited.
Adopted by
Most recently taken up by
- Dimon94/dveritytheir own version, first seen Nov 8, 2026
- Dimon94/skillstheir own version, first seen Nov 8, 2026
- The-Vibe-Company/quivrtheir own version, first seen Nov 8, 2026
- 5thlayer/skillworkstheir own version, first seen Nov 8, 2026
- zhikedan/mattpocock-skills-dshtheir own version, first seen Nov 8, 2026
- protokol11/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use setup-ts-deep-modules, to-questionnaire 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.
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 43 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 90 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 49 projects that use this
AWSSkillwizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
Also in 116 projects that use this
ryotaroh180105Skillclaude-handoff
Hand the current conversation off to a fresh background agent that picks up the work immediately.
Also in 39 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 51 projects that use this
- +2 more from aws
Other versions194 projects use a version of this.
Word for word · 0
None found.
Edited · 3
- WenWuZhiDao/mattpocock-skills-zh★ 2714% same
- T-miracle/codex-skills-zh★ 513% same
- longfangsong/skills★ 210% same
Wrote their own version · 191
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- formbricks/formbricks★ 13ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- bestofjs/bestofjs★ 3.1ksame name
- moeru-ai/xsai★ 667same name
- DanMcInerney/architect-loop★ 626same name
181 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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- dispatch-ticketsSkill
- grill-with-docsSkill
- implementSkill
- improve-codebase-architectureSkill
- orchestrateSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- setup-omskillsSkill
- tddSkill
- to-ticketsSkill
- triageSkill
- wayfinderSkill
- cavemanSkill
- designSkill
- excalidrawSkill
- grill-meSkill
- handoffSkill
- model-routingSkill
- prompt-comprehension-auditsSkill
- teachSkill
- tmux-workerSkill
- voiceSkill
- wormholeSkill
- write-a-skillSkill
- writing-great-skillsSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 182 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Before reading relative links, run cd '<loaded-skill-directory>' && pwd -P with this loaded file's directory to obtain the physical base, …
- Very specific: line 21
Read the configured issue tracker.
- Distinctive: line 38
If the repository has not already been inspected in this context, inspect the current implementation in the affected area.
- Distinctive: line 42
Search the configured issue tracker by domain concept and cited relationships for an existing Spec that already governs the result.
- Very specific: line 55
Write the Spec with the template below.
- Distinctive: line 89
Do not include file paths or code snippets.
- Distinctive: line 112
After the new or updated Spec durably incorporates every accepted Scratchpad item that should survive, the supplied Scratchpad file may be …
“Common” is measured: kept by at least 6 in 10 of the 182 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
To Spec
Before reading relative links, run cd '<loaded-skill-directory>' && pwd -P
with this loaded file's directory to obtain the physical base, then resolve
links against that printed directory. Resolve the source symlink before applying
... Read linked files even when their skills are absent from the discovery
list.
Produce a new or updated Spec from information already established in the conversation, repository, or a supplied Scratchpad. Do not conduct a requirements interview, invent decisions, or treat the Spec as an implementation unit.
Read the configured issue tracker. If configuration is unavailable, follow setup-omskills and its scoped authorization gate before continuing, including in headless runs. Respect read-only roles and return unresolved prerequisites to the responsible caller.
A supplied Scratchpad is source context, not implementation authority. Read it completely. Preserve its explicit established decisions, constraints, exclusions, unresolved Questions, and evidence pointers without treating an unresolved Question or recommendation as a decision. Do not fill gaps from an imagined prior conversation.
Process
- Gather all supplied source context. When a Scratchpad is supplied, distinguish its established content from its unresolved Questions before synthesis.
- If the repository has not already been inspected in this context, inspect the current implementation in the affected area. Use the project's domain glossary terms throughout the Spec and preserve applicable ADR decisions.
- Search the configured issue tracker by domain concept and cited relationships for an existing Spec that already governs the result. If one exists, read its complete body and comments and update it instead of creating a duplicate. Preserve accepted content outside the synthesized change.
- Record test seams, interfaces, architecture hints, and other implementation guidance only when the supplied context or repository has already established them. Preserve established ordering, concurrency, and shared-resource constraints; to-tickets decides execution during decomposition and records it in the Tickets. Mark missing implementation decisions as unresolved rather than inventing them or interviewing the user during synthesis.
- Write the Spec with the template below. Update the governing Spec found in
step 3, or publish one new planning issue when none exists. Add no
implementation-readiness state:
to-ticketsmust first decompose the Spec into independently auditable Tickets.
<spec-template>Problem Statement
<the established problem from the user's perspective>
Solution
<the established solution from the user's perspective>
User Stories
<an extensive numbered list covering every established aspect of the feature; include each distinct actor goal or user-visible outcome, with established success, failure, and edge outcomes as separate stories when they produce different user-visible results; include no unstated requirements>
- As an
<actor>, I want<feature>, so that<benefit>.
<user-story-example>
1. As a mobile bank customer, I want to see the balance on my accounts, so that I can make informed spending decisions.
</user-story-example>Implementation Decisions
<a bullet list of the implementation decisions already established, including applicable modules and interfaces, technical clarifications, architecture, schema changes, contracts, and interactions>
Do not include file paths or code snippets. Exception: when prototype output contains a state machine, reducer, schema, type shape, or other snippet that encodes an established decision more precisely than prose can, include only its decision-bearing parts and identify it as prototype output.
Testing Guidance
- Established test seams: <caller-visible seams already established, or "Not yet established">
- Observable behavior:
<the outcomes later Tickets must preserve and verify> - Prior art: <existing repository tests already identified, or "None identified">
Out of Scope
<the source-supported boundaries of what is out of scope>Further Notes
<remaining established information that does not fit another section, or "None">
</spec-template>- After the new or updated Spec durably incorporates every accepted Scratchpad item that should survive, the supplied Scratchpad file may be removed. Preserve it when unresolved continuation context still depends on it; never delete it before checking the durable artifact.
Publishing is complete when the new or updated Spec contains every established requirement and decision, introduces no new requirement, identifies unresolved implementation details honestly, preserves unrelated accepted content, and carries no implementation-readiness state. A published Spec creates neither Ticket readiness nor Mission authorization; later ticketing, triage, Prompt Audit, and explicit selection remain separate phases.
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.

