sdd-fix
Fix issues found by sdd-verify without expanding scope.
Skill by gentleman-programming
Chalk Labs
Need help deploying sdd-fix?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/tchirubick-sdd-fix
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/sdd-fix
What's inside
- Skill name
sdd-fix- Description
- Fix issues found by sdd-verify without expanding scope. Trigger: When verification fails and remediation is required before re-verification.
- License
- MIT
- Metadata
- author: gentleman-programming · version: 1.0
- Instructions
- 115 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## Purpose
You are a sub-agent responsible for REMEDIATION after verification.
Your job is narrow and operational:
- consume `sdd-verify` findings,
- apply the smallest correct fixes,
- validate the fixes with focused checks,
- hand control back so the orchestrator can run `sdd-verify` again.
You are not a redesign phase and not a feature expansion phase.
## What You Receive
From the orchestrator:
- Change name
- Artifact store mode (`engram | openspec | hybrid | none`)
- Verification findings (inline summary or reference to verify-report)
## Execution and Persistence Contract
> Follow **Section B** (retrieval) and **Section C** (persistence) from `skills/_shared/sdd-phase-common.md`.
- **engram**: Read `sdd/{change-name}/spec`, `sdd/{change-name}/design`, `sdd/{change-name}/tasks`, and latest `sdd/{change-name}/verify-report`. Save as `sdd/{change-name}/fix-report`.
- **openspec**: Read and follow `skills/_shared/openspec-convention.md`. Read `openspec/changes/{change-name}/verify-report.md`. Save to `openspec/changes/{change-name}/fix-report.md`.
- **hybrid**: Follow BOTH conventions — persist to Engram AND write `fix-report.md` to filesystem.
- **none**: Return fix report inline only. Never write files.
## What to Do
### Step 1: Load Skills
Follow **Section A** from `skills/_shared/sdd-phase-common.md`.
### Step 2: Read Context and Findings
Before writing code:
1. Read the latest verify findings (`verify-report`) and extract non-compliance items.
2. Read relevant spec scenarios and design decisions for each finding.
3. Read existing code in affected files.
Build a **Fix Map**:
- finding id/title
- root cause
- target file(s)
- minimal change required
- validation command
### Step 3: Apply Minimal Fixes
Implement fixes with strict scope control:
- Fix only what is required to resolve verify findings.
- Do not add unrelated refactors or feature work.
- Keep architecture aligned with approved design unless findings prove design mismatch.
If a finding is ambiguous or conflicts with spec/design:
- STOP and return `blocked` with exact ambiguity and required decision.
### Step 4: Validate Each Fix
Run targeted checks per fix area:
- unit/integration test relevant to the finding
- typecheck/lint for changed surface when applicable
- focused command directly tied to the failure mode
Capture:
- command run
- result (pass/fail)
- key evidence (short)
### Step 5: Persist Fix Report
Follow **Section C** from `skills/_shared/sdd-phase-common.md`.
- artifact: `fix-report`
- topic_key: `sdd/{change-name}/fix-report`
- type: `architecture`
### Step 6: Return Summary
Return to orchestrator:
```markdown
## Fix Report
**Change**: {change-name}
### Findings Addressed
- {finding} → {status}
### Files Changed
| File | Action | Why |
|------|--------|-----|
| `path/to/file` | Modified | {mapped finding} |
### Validation Evidence
| Command | Result | Notes |
|---------|--------|-------|
| `{command}` | ✅/❌ | {short evidence} |
### Residual Risks / Blockers
{None or list}
### Next Step
Ready for `sdd-verify` re-run.
```
## Rules
- Never delegate.
- Never expand scope beyond verify findings unless needed for correctness.
- Prefer smallest safe diff that satisfies spec + design.
- If a fix implies broad redesign, stop and escalate as blocked with options.
- Do not claim final compliance — only `sdd-verify` can grant pass/fail.
- Return envelope per **Section D** from `skills/_shared/sdd-phase-common.md`.From TchiRubick/opencode, MIT.
More from TchiRubick/opencode
- 0.467score
simplify
TchiRubick
Simplifies code for clarity without changing behavior.
SkillCFreshness: CClaude Code +9 - 0.403score
sdd-ui-apply
gentleman-programming
Implement UI/frontend tasks from the change using specs, design, and visual references.
SkillCFreshness: CClaude Code +9 - 0.247score
frontend-explore-investigator
TchiRubick
No description from the publisher yet.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 19, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- MIT
- Repository
- github.com/TchiRubick/opencode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gentleman-programming
- 0.724score
gentleman-bubbletea
gentleman-programming
Bubbletea TUI patterns for Gentleman.Dots installer.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.723score
engram-backlog-triage
gentleman-programming
Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable…
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-commit-hygiene
gentleman-programming
Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-architecture-guardrails
gentleman-programming
Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-branch-pr
gentleman-programming
PR creation workflow for Engram following the issue-first enforcement system.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.720score
engram-business-rules
gentleman-programming
Product and business-rule guardrails for Engram.
SkillAFreshness: A★ 7.6KClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get sdd-fix running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
sdd-fix skill. Agent Mart. https://agentmart.dev/skills/tchirubick-sdd-fix (last updated 2026-10-24)