dx-review-triage
Triage findings from a review report and apply the fixes you choose.
Skill by dikamilo
Chalk Labs
Need help deploying dx-review-triage?
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/dikamilo-dx-review-triage
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
Use cases: documents
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 and code. 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/dx-review-triage
What's inside
- Skill name
dx-review-triage- Description
- Triage findings from a review report and apply the fixes you choose.
- License
- MIT
- Instructions
- 51 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# dx-review-triage Turn a review report's findings into decisions — and, when you say so, into edits. Every review (`dx-review`) only analyzes and reports; this is the one place that **acts** on a finding, one finding at a time, only on your confirmation. **Guard.** Resolve `<container-id>` under `context/changes/` or `context/efforts/`. If it resolves under `context/archive/` instead, refuse: archived work is done. If `reviews/` is missing or holds no report, point at `/dx-review <policy-id> <container-id>`. ## 1 — Resolve which report A report lives at `reviews/<policy-id>.md`, one per Policy, always the current review because a re-run overwrites it. - **A policy ID given** → `reviews/<policy-id>.md`. If the file is missing, name it and list the reports that exist. - **No policy ID** → exactly one report → use it; several → ask which, since each can carry open findings at once. A legacy `reviews/impl-review.md` or `reviews/plan-review.md` is never read and doesn't count as a report: if one is all there is, say it's superseded and point at `/dx-review implementation <container-id>` or `/dx-review plan <container-id>` respectively. ## Load first The report's schema — the finding/`Resolution` format, the resume rule, the never-commit rule — is `context/config/templates/review-report.md` (missing → `/dx-init`). ## 2 — Walk findings in order Resume at the first finding with `Resolution: PENDING`, document order. Load what that finding's **Location** names — a plan section → `plan.md`; a `file:line` → that file plus enough surrounding code or `git log` to judge the fix — and nothing for findings you skip. Show its title, location, detail, and suggested fix, then ask: - **Fix now** — apply the suggested fix (or a variant you propose); show the before/after edit first, apply on confirmation. - **Fix differently** — ask what they'd prefer instead, apply that. - **Skip** — leave it for now, move on. - **Accept risk** — leave it, record the one-line reason. - **Record as lesson** — hand the finding's title and detail to `/dx-lesson`'s entry shape and tell the user to confirm there. Never append to `foundation/lessons.md` yourself — that file has exactly one writer. Immediately rewrite that finding's `Resolution:` line in place per the schema. If an edit you already applied for an earlier finding also resolves a later one, mark the later finding `FIXED` too, pointing at the same edit — don't manufacture a redundant second edit or commit. ## 3 — Commit what the fix touched, never the report Decide per applied fix, from the files it changed: - **Touched files outside `context/`** (shipped code, docs, config) → commit that fix on its own, the Conventional Commit shape `dx-implement` uses: `fix(<container-id>): <finding title> (review)`. Stage only those files. - **Touched only `context/` artifacts** (`plan.md`, `frame.md`, …) → don't commit. Those are working state the user commits on their own schedule. - **The report itself** is never committed. ## On disagreement If applying a fix would contradict something the plan or a standard states elsewhere, stop and say so — don't silently pick a side. ## Done when Every finding in the resolved report has a `Resolution:` other than `PENDING` — or you've stopped partway, which is fine, since re-running resumes from the next pending one. Print a one-line tally and stop, no auto-chain: ``` Triaged <report file>: <n> fixed, <n> skipped, <n> accepted, <n> dismissed Next: /dx-review <policy-id> <container-id> — re-review after fixes or: <each line of the Policy's ## Next> ```
From dikamilo/dx-workflow, MIT.
More from dikamilo/dx-workflow
- 0.628score
dx-brainstorm
dikamilo
Think through a raw idea before committing to it — weigh alternatives, price doing nothing, and route to a change, an effort, or nothing at all.
SkillAFreshness: A★ 8Claude Code +9 - 0.628score
dx-distill
dikamilo
Run a discovery conversation and write a brief — the problem, the evidence behind it, the scope, the decisions, and the next uncertainty to resolve.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
dx-diagnose
dikamilo
Feedback-loop-first diagnosis for bugs and performance regressions.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
dx-references
dikamilo
Loads one or more dx shared reference documents by topic (space-separated, one call).
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
dx-domain
dikamilo
Actively sharpen the ubiquitous language in foundation/glossary.md.
SkillAFreshness: A★ 8Claude Code +9 - 0.624score
dx-standards-update
dikamilo
Create, edit, or promote a standard in context/standards/ — from the conversation, a graduated lesson, or another project.
SkillAFreshness: A★ 8Claude Code +9 - 0.624score
dx-frame
dikamilo
Interview to settle the problem framing, alternatives, and user cases for a change or effort before planning — writes frame.md.
SkillAFreshness: A★ 8Claude Code +9 - 0.621score
dx-roadmap
dikamilo
Decompose an effort into an ordered list of vertical slices and write roadmap.md.
SkillAFreshness: A★ 8Claude Code +9 - 0.621score
dx-standards-discover
dikamilo
Mine the project's real conventions from tooling, code, and docs and write them into the standards layer.
SkillAFreshness: A★ 8Claude Code +9 - 0.621score
dx-refactor-discover
dikamilo
Hunt the codebase for refactor opportunities, present them inline, and promote the ones you pick into changes.
SkillAFreshness: A★ 8Claude Code +9 - 0.621score
dx-research
dikamilo
Investigate one topic — codebase or external doc — and write it down with provenance for a plan to lean on.
SkillAFreshness: A★ 8Claude Code +9 - 0.621score
dx-archive
dikamilo
Archive a completed change or effort — move its folder to context/archive/ and stamp it archived.
SkillAFreshness: A★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 4
- Open issues
- 0
- Last commit (this folder)
- Oct 7, 2026 (24 days ago)
- Last release
- Oct 7, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dikamilo/dx-workflow
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dikamilo
- 0.628score
dx-brainstorm
dikamilo
Think through a raw idea before committing to it — weigh alternatives, price doing nothing, and route to a change, an effort, or nothing at all.
SkillAFreshness: A★ 8Claude Code +9 - 0.628score
dx-distill
dikamilo
Run a discovery conversation and write a brief — the problem, the evidence behind it, the scope, the decisions, and the next uncertainty to resolve.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
dx-references
dikamilo
Loads one or more dx shared reference documents by topic (space-separated, one call).
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
dx-domain
dikamilo
Actively sharpen the ubiquitous language in foundation/glossary.md.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
dx-diagnose
dikamilo
Feedback-loop-first diagnosis for bugs and performance regressions.
SkillAFreshness: A★ 8Claude Code +9 - 0.624score
dx-frame
dikamilo
Interview to settle the problem framing, alternatives, and user cases for a change or effort before planning — writes frame.md.
SkillAFreshness: A★ 8Claude 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 dx-review-triage 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
dx-review-triage skill. Agent Mart. https://agentmart.dev/skills/dikamilo-dx-review-triage (last updated 2026-10-24)