bounds-review
Review a pinned diff or change for correctness, requirement compliance, and maintainability, separating actionable findings from preferences and unverified…
Skill by boundsj
Chalk Labs
Need help deploying bounds-review?
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/boundsj-bounds-review
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: security
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/bounds-review
What's inside
- Skill name
bounds-review- Description
- Review a pinned diff or change for correctness, requirement compliance, and maintainability, separating actionable findings from preferences and unverified assumptions.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (4)
- LICENSE.txt
- NOTICE.md
- SKILL.md
- protocol.md · references/
SKILL.md (first lines)
# Bounds review Resolve the requested base and head to commit SHAs before reviewing. For a branch or PR, record the merge-base and review `git diff <merge-base-sha> <head-sha>`; if the user requested a literal endpoint comparison, use that instead. Validate refs and note an empty diff. Infer the base from the PR or repository when clear; ask only if the choice changes the review materially. For uncommitted work, capture the staged and unstaged diff plus relevant untracked files as a fixed snapshot outside the change. Record its identity and HEAD; do not pretend HEAD includes local edits. Read [review protocol](references/protocol.md) for snapshot details or delegated review. Find the applicable request/spec and project conventions. If requirements are unavailable, state that limitation and still review the code. Check: - **Correctness:** failing inputs, state transitions, error paths, compatibility, and tests that could miss a real defect. - **Requirements:** missing behavior, unintended scope, and retained behavior at risk. - **Maintainability:** concrete costs in the changed paths, judged against the project's conventions. Preferences are optional observations. Use one independent reviewer for consequential changes when delegation is available and permitted by existing user and host instructions. Reuse authorization already granted; do not ask for it again. Add another only for consequential uncertainty or disputed findings. Discover capabilities and follow the linked protocol. Never silently swap a requested provider/model. Timeout, failure, or silence is not approval. If no reviewer can start, supply the protocol’s review packet and label any local review accurately. Assign stable finding IDs across rounds. Use **blocker** for a broken intended case or critical safety failure, **should** for a concrete in-scope defect, and **nit** for optional improvements. Give severity, file/line, trigger, consequence, evidence, and a focused correction. Distinguish executed checks, source-based reasoning, and assumptions. Evaluate findings on their evidence rather than reviewer agreement. State “no actionable findings” when appropriate, with coverage limits. A review request returns findings; it does not authorize edits or publishing comments. When fixes are authorized, rerun affected checks and review the changed head. Bound the process to two fix/review cycles unless the user specifies otherwise; report unresolved issues at the limit.
From boundsj/bounds-skills, MIT.
More from boundsj/bounds-skills
- 0.570score
bounds-architect
boundsj
Design state ownership, types, interfaces, and module shape before implementing a nontrivial change, comparing a few meaningful alternatives with…
SkillAFreshness: AClaude Code +9 - 0.570score
bounds-automate-me
boundsj
Create or update a scoped skill that captures how the user likes agents to work, from their explicit preferences and bounded evidence of repeated decisions.
SkillAFreshness: AClaude Code +9 - 0.570score
bounds-mode
boundsj
Coordinate a task with Bounds workflows when the user explicitly asks for bounds-mode.
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-why
boundsj
Investigate why existing code, a design, a threshold, or a past decision has its current shape, separating cited evidence from inference, alternatives, and…
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-create-verification
boundsj
Create and execute a project-local verification recipe and small feature map using the project's existing tools to launch, health-check, drive, capture…
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-recall
boundsj
Recover prior goals, decisions, constraints, and unfinished work from accessible agent sessions and project records, then verify current state.
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-retro
boundsj
Examine a bounded set of accessible engineering work for repeated corrections and wasted effort, then propose evidence-backed improvements to structure…
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-unslop
boundsj
Edit prose the user asks to tighten so it reads direct and concrete, preserving meaning, commitments, numbers, uncertainty, citations, quotes, and code.
SkillAFreshness: AClaude Code +9 - 0.561score
bounds-debug
boundsj
Reproduce an observed bug or performance regression, isolate its cause, fix it within scope, and verify the user's failing behavior with a repeatable check.
SkillAFreshness: AClaude Code +9 - 0.561score
bounds-how
boundsj
Explain how existing code, a subsystem, or a change works, from entrypoint through data and state to boundaries and outcome, sized to the reader's purpose.
SkillAFreshness: AClaude Code +9 - 0.561score
bounds-ketchup
boundsj
Brief the user on what changed in the current conversation since their last substantive message: current state, evidence, blockers, decisions they own, and…
SkillAFreshness: AClaude Code +9 - 0.561score
bounds-plan
boundsj
Turn an engineering idea or change request into a concise, executable plan with scope, retained behavior, acceptance checks, and real dependencies.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 4, 2026 (26 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/boundsj/bounds-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from boundsj
- 0.570score
bounds-mode
boundsj
Coordinate a task with Bounds workflows when the user explicitly asks for bounds-mode.
SkillAFreshness: AClaude Code +9 - 0.570score
bounds-automate-me
boundsj
Create or update a scoped skill that captures how the user likes agents to work, from their explicit preferences and bounded evidence of repeated decisions.
SkillAFreshness: AClaude Code +9 - 0.570score
bounds-architect
boundsj
Design state ownership, types, interfaces, and module shape before implementing a nontrivial change, comparing a few meaningful alternatives with…
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-create-verification
boundsj
Create and execute a project-local verification recipe and small feature map using the project's existing tools to launch, health-check, drive, capture…
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-recall
boundsj
Recover prior goals, decisions, constraints, and unfinished work from accessible agent sessions and project records, then verify current state.
SkillAFreshness: AClaude Code +9 - 0.567score
bounds-retro
boundsj
Examine a bounded set of accessible engineering work for repeated corrections and wasted effort, then propose evidence-backed improvements to structure…
SkillAFreshness: AClaude 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 bounds-review 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
bounds-review skill. Agent Mart. https://agentmart.dev/skills/boundsj-bounds-review (last updated 2026-10-24)