Agent skill
done-sichengchen-esper
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/done-sichengchen-esper
SKILL.md
Add esper:review skill for code quality review
Context
esper currently has no skill for reviewing code before shipping. The /esper:ship skill pushes and opens a PR, but there is no structured code review step. An esper:review skill would let users get code quality feedback on their branch diff before shipping, catching issues early.
The skill should work at the branch/PR level — reviewing the diff between the current branch and main, focused on code quality (bugs, style, security, complexity).
Approach
-
Create
skills/esper-review/SKILL.mdwith the following workflow:- Step 1: Check setup — run
esperkit config check, determine current branch and base branch - Step 2: Gather diff — run
git diff main...HEAD(or the appropriate base) to get the full branch diff. If a PR number is provided as argument, usegh pr diff <number>instead - Step 3: Read context — read
.esper/CONSTITUTION.mdfor project principles. If there's an active plan, read it for intent context (what the code is supposed to do) - Step 4: Review — analyze the diff for:
- Bugs and logic errors
- Security issues (OWASP top 10)
- Code style and consistency with existing patterns
- Missing error handling or edge cases
- Unnecessary complexity or dead code
- Step 5: Report — print a structured review with sections for each category. Use severity levels (critical, warning, note). Include file paths and line references
- Step 6: Offer fixes — if actionable issues were found, use
AskUserQuestionto ask if the user wants to create/esper:fixplans for them. If yes, batch the selected issues into fix plans (one per issue or grouped by file/concern, at the user's preference)
- Step 1: Check setup — run
-
No changes to
bin/cli.js— the installer auto-discovers new skill directories.
Files to change
skills/esper-review/SKILL.md(create — the skill definition)
Verification
- Run:
node --test test/ - Expected: existing tests still pass
- Edge cases: handle empty diffs (nothing to review), very large diffs (summarize rather than line-by-line), and PRs with no active plan context
Progress
- Created
skills/esper-review/SKILL.mdwith 6-step workflow (check, gather diff, read context, review, report, offer fixes) - Modified: skills/esper-review/SKILL.md
- Verification: 64/64 tests pass
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?