reviewing-spec-implementations
Review changes since a fixed point against the originating spec.
Skill by supagetto
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/supagetto-reviewing-spec-implementations
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/reviewing-spec-implementations
What's inside
- Skill name
reviewing-spec-implementations- Description
- Review changes since a fixed point against the originating spec. Reports missing requirements, scope creep, and incorrect implementations. Use when the user says "review implementation".
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Review the diff between `HEAD` and a fixed point the user supplies, checking whether the code faithfully implements the originating spec. ## Process ### 1. Pin the fixed point Use whatever the user said as the fixed point (a commit SHA, branch name, tag, `main`, `HEAD~5`, etc.). If they didn't specify one, ask. Capture the diff once: ```sh git diff <fixed-point>...HEAD ``` Three-dot so the comparison is against the merge-base. Also capture the commit list: ```sh git log <fixed-point>..HEAD --oneline ``` Before going further, confirm the fixed point resolves (`git rev-parse <fixed-point>`) and the diff is non-empty. A bad ref or empty diff should fail here, not later. ### 2. Identify the spec Look for the originating spec in this order: 1. A path the user passed as an argument. 2. A spec matching the current repo and branch (see the using-workbench skill for location and naming conventions). 3. If nothing is found, ask the user. If there is no spec, stop — there is nothing to review against. ### 3. Review the diff against the spec For every requirement in the spec, check the diff and report: - **Missing**: requirements the spec asked for that are absent or only partially implemented. - **Scope creep**: behaviour in the diff that the spec did not ask for. - **Wrong**: requirements that look implemented but where the implementation contradicts what the spec described. Quote the spec line for each finding. Keep the review under 400 words. Done when every requirement in the spec has been checked. ### 4. Report Present findings under a single `## Spec Review` heading. End with a one-line summary: total findings and the worst issue (if any).
From supagetto/README.ai, MIT.
More from supagetto/README.ai
- 0.570score
setting-up-graft
supagetto
Use when graft/ or .serena/ is not git-ignored, or graft cards are not greppable by ripgrep, or the user asks to set up graft.
SkillAFreshness: AClaude Code +9 - 0.569score
reading-web-pages
supagetto
Read the main content of a web page URL as markdown.
SkillAFreshness: AClaude Code +9 - 0.565score
huddling
supagetto
Pressure-test a decision with a crew of five voices who answer independently, peer-review each other anonymously, and get a verdict from bigbrain.
SkillAFreshness: AClaude Code +9 - 0.564score
removing-ai-tells
supagetto
Remove AI tells from prose.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-tasks
supagetto
Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges.
SkillAFreshness: AClaude Code +9 - 0.564score
implementing-specs
supagetto
Implement work from a spec and its tasks.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-specs
supagetto
Synthesize the current conversation into a spec.
SkillAFreshness: AClaude Code +9 - 0.564score
writing-commit-messages
supagetto
Use when writing a commit message or when the user says "commit change".
SkillAFreshness: AClaude Code +9 - 0.564score
creating-questionnaires
supagetto
Create a questionnaire for someone else to fill in.
SkillAFreshness: AClaude Code +9 - 0.560score
describing-changes
supagetto
Use when showing the shape of a change as pseudocode views.
SkillAFreshness: AClaude Code +9 - 0.559score
requesting-clarification
supagetto
Use when the user signals confusion about your last message, including short interjections like "wait", "what", "huh", or "again".
SkillAFreshness: AClaude Code +9 - 0.559score
resolving-merge-conflicts
supagetto
Use when resolving an in-progress git merge/rebase conflict, or when the user says "resolve merge conflict" or "fix merge conflict".
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/supagetto/README.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from supagetto
- 0.570score
setting-up-graft
supagetto
Use when graft/ or .serena/ is not git-ignored, or graft cards are not greppable by ripgrep, or the user asks to set up graft.
SkillAFreshness: AClaude Code +9 - 0.569score
reading-web-pages
supagetto
Read the main content of a web page URL as markdown.
SkillAFreshness: AClaude Code +9 - 0.565score
huddling
supagetto
Pressure-test a decision with a crew of five voices who answer independently, peer-review each other anonymously, and get a verdict from bigbrain.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-tasks
supagetto
Break a plan, spec, or conversation into tracer-bullet tasks with blocking edges.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-specs
supagetto
Synthesize the current conversation into a spec.
SkillAFreshness: AClaude Code +9 - 0.564score
creating-questionnaires
supagetto
Create a questionnaire for someone else to fill in.
SkillAFreshness: AClaude Code +9
Cite this page
reviewing-spec-implementations skill. Agent Mart. https://agentmart.dev/skills/supagetto-reviewing-spec-implementations (last updated 2026-10-24)