create-tech-spec
Skill313 starsChanged 5 months agoMITView on GitHub
Create a technical spec from a GitHub issue in this repository by applying the shared `write-tech-spec` workflow with Oz-specific issue context and output paths. Use when an issue should be turned into a tech spec artifact stored under `specs/GH<issue-number>/tech.md` and the agent should prepare file changes only, without creating commits or pull requests itself unless a cloud workflow explicitly asks for it.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- flopperj/dotfiles-coretheir own version, first seen Nov 4, 2026
- shiggydoodah/skillstheir own version, first seen Aug 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- flopperj/dotfiles-core★ 3same name
- shiggydoodah/skills★ 2same name
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 repository17 other files it gives its agents.
- bootstrap-issue-configSkill
- create-product-specSkill
- dedupe-issue-localSkill
- dedupe-issueSkill
- evaluate-auto-implement-eligibilitySkill
- implement-issueSkill
- review-pr-localSkill
- review-spec-localSkill
- review-specSkill
- security-review-prSkill
- security-review-specSkill
- triage-issue-localSkill
- triage-issueSkill
- update-dedupeSkill
- update-pr-reviewSkill
- update-triageSkill
- verify-prSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. About 0 are common, 8 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create a tech spec from a GitHub issue for this repository.
- Distinctive: line 16
Use that shared skill as the base behavior and structure unless this wrapper overrides it.
- Distinctive: line 24
do not create or edit Linear issues as part of this workflow
- Very specific: line 30
When available, the product spec at specs/GH<issue-number>/product.md should be treated as the primary input for understanding the intended …
- Very specific: line 34
Start from the shared write-tech-spec guidance and follow its structure and writing standards unless this wrapper says otherwise.
- Very specific: line 35
Read the issue details carefully.
- Very specific: line 37
Create or update specs/GH<issue-number>/tech.md.
- Distinctive: line 38
Use the shared skill's structure as the baseline, adapted to this repository and issue format.
- Distinctive: line 46
follow-ups or open technical questions
- Distinctive: line 47
Keep the tech spec concise, actionable, and grounded in actual code paths and ownership boundaries in this repository.
- Very specific: line 49
Do not include issue number references (e.g.
- Distinctive: line 56
Leave the repository with the new or updated tech spec file ready to be committed by the workflow.
- Very specific: line 57
When requested by the prompt, leave a ready-to-use pr-metadata.json with branch_name, pr_title, and pr_summary.
- Distinctive: line 58
If the issue is underspecified, still produce the best possible tech spec and clearly capture assumptions or open questions in the spec …
≈ “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
create-tech-spec
Create a tech spec from a GitHub issue for this repository.
Overview
This skill is a thin Oz wrapper around the shared tech-spec workflow:
write-tech-spec
Use that shared skill as the base behavior and structure unless this wrapper overrides it. Keep the same emphasis on grounding the plan in current code, documenting relevant files and data flow, explaining tradeoffs, and defining validation.
The Oz-specific differences are:
- the primary input is a GitHub issue, not a Linear issue
- the output path is
specs/GH<issue-number>/tech.md issue_comments.mdand triggering-comment context are additional design inputs- a workflow may also request a structured PR metadata file in
pr-metadata.json - do not create or edit Linear issues as part of this workflow
Inputs
Expect issue details in the prompt, including the issue number, title, description, labels, assignees, and optional prior discussion captured in issue_comments.md.
When available, the product spec at specs/GH<issue-number>/product.md should be treated as the primary input for understanding the intended behavior. The tech spec translates that product intent into an implementation approach.
Process
- Start from the shared
write-tech-specguidance and follow its structure and writing standards unless this wrapper says otherwise. - Read the issue details carefully. If a product spec exists at
specs/GH<issue-number>/product.md, read it first to understand the intended behavior. Ifissue_comments.mdexists, review it for clarifications, prior decisions, and design nuance that should influence the tech plan. - Inspect the repository to understand the current implementation and the likely scope of the requested work before writing the spec. Do not guess about current architecture when the code can be inspected directly.
- Create or update
specs/GH<issue-number>/tech.md. - Use the shared skill's structure as the baseline, adapted to this repository and issue format. At minimum, cover:
- problem
- relevant code
- current state
- proposed changes
- end-to-end flow when useful
- risks and mitigations
- testing and validation
- follow-ups or open technical questions
- Keep the tech spec concise, actionable, and grounded in actual code paths and ownership boundaries in this repository.
- Do not implement the feature or modify production code as part of this task. Limit changes to the tech spec artifact and any minimal repository metadata needed to support it. Treat temporary context files such as
issue_comments.mdas scratch input only and do not commit them. - Do not include issue number references (e.g.
(#N),Refs #N) in commit messages. The issue is already linked in the PR. - If the prompt asks for it, write
pr-metadata.jsonat the repository root containing a JSON object with the fieldsbranch_name,pr_title, andpr_summary. Thepr_summaryshould summarize the resulting spec changes, validation, and any reviewer-relevant assumptions or open questions. For spec-only PRs, include a non-closing reference to the source issue such asRelated issue: #<issue-number>rather than closing keywords likeClosesorFixes. - Default behavior: do not stage files, create commits, push branches, open pull requests, or use the GitHub CLI. If the prompt explicitly instructs you to publish a named branch, you may commit and push exactly the requested spec changes to that branch, but still do not open or update the pull request yourself unless the prompt explicitly asks for it.
- In your final response, provide a brief summary of the tech spec and call out any assumptions or open questions so the workflow can reuse that summary when creating the PR.
Outputs
- Leave the repository with the new or updated tech spec file ready to be committed by the workflow.
- When requested by the prompt, leave a ready-to-use
pr-metadata.jsonwithbranch_name,pr_title, andpr_summary. - If the issue is underspecified, still produce the best possible tech spec and clearly capture assumptions or open questions in the spec file and final response.
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.

