claude-sense-check
Skill9 starsChanged 3 months agoMITView on GitHub
Incremental code logic verification of UAT test cases — pick batch, trace code, fix issues, update tracking.
In this repository56 other files it gives its agents.
- .claude/agents/CLAUDE.mdCLAUDE.md
- .claude/hooks/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .claude/prompts/CLAUDE.mdCLAUDE.md
- .claude/rules/CLAUDE.mdCLAUDE.md
- .claude/skills/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- vision/CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- scaffold/llms.txtllms.txt
- architecture-checkSkill
- backlog-reviewSkill
- bootstrapSkill
- brainstormSkill
- buildSkill
- code-qualitySkill
- commitSkill
- continueSkill
- custom-hooksSkill
- dashboardSkill
- debug-sessionSkill
- deploySkill
- discoverSkill
- doctorSkill
- fix-issueSkill
- framework-upgradeSkill
- handoffSkill
- help-meSkill
- ideateSkill
- lanesSkill
- manual-testSkill
- merge-downSkill
- merge-upSkill
- optimizeSkill
- parallel-workSkill
- performance-checkSkill
- phase-reviewSkill
- pr-statusSkill
- quality-checkSkill
- quickstartSkill
- refine-loopSkill
- researchSkill
- retrospectiveSkill
- security-auditSkill
- skill-createSkill
- skill-evalSkill
- sprint-endSkill
- sprint-startSkill
- story-cycleSkill
- testing-cycleSkill
- test-validatorSkill
- UAT-cycleSkill
- undo-workSkill
- uninstallSkill
- weekly-maintenanceSkill
- wrap-upSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 14 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 24
If all cases are checked, report "All UAT cases have been sense-checked" and stop
- Distinctive: line 40
Before checking any logic, collect the full picture for the batch's feature area:
- Distinctive: line 42
Read all source files relevant to the batch
- Distinctive: line 45
Read existing tests for the relevant code — they reveal intent and edge cases
- Distinctive: line 46
Check the Covers field on each test case to identify which backlog stories are involved
- Distinctive: line 47
Read the story acceptance criteria from the relevant epic/backlog file
- Distinctive: line 49
Do NOT proceed to logic checks until you have the full picture.
- Distinctive: line 55
Read the test case steps and acceptance criteria carefully
- Very specific: line 78
Check the Claude Sense Check checkbox: - [x] Logic verified from code perspective
- Distinctive: line 86
After updating the tracking file, update any status summary tables to reflect the new sense-check counts.
- Distinctive: line 129
Never re-check an already checked case
- Distinctive: line 130
Never check more than 5 cases in one run — stay focused
- Distinctive: line 131
Always update the tracking file before finishing — the checkboxes are the source of truth
- Distinctive: line 132
Always gather full context before starting logic checks — no guessing
- Very specific: line 133
Always use /story-cycle for fixes — maintain TDD discipline
- Very specific: line 134
Follow coding standards in docs/reference/CODING_STANDARDS.md
- Distinctive: line 135
Follow verification rules: run the project's test command before claiming fixes are complete
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
claude-sense-check
Performing incremental Claude Sense Check on UAT backlog.
Phase 1: Read Current State
- Find the UAT tracking file: check for
docs/testing/UAT_COVERAGE.md,docs/testing/UAT_INDEX.md, ordocs/testing/uat/directory - Scan for Claude Sense Check sections in every test case
- Build a work queue: cases where
- [ ] Logic verified from code perspectiveis unchecked - Skip cases where the checkbox is already
[x] - If all cases are checked, report "All UAT cases have been sense-checked" and stop
Phase 2: Pick Next Batch
From the unchecked cases, sorted by priority (critical > high > medium > low), then by ID within each priority level:
- Select 2-5 cases that share the same module, feature area, or user flow
- Present to the user:
- Batch: which cases (e.g., UAT-005, UAT-006, UAT-007)
- Area: the functional area they belong to
- Rationale: why they belong together
- Relevant files: source files and components expected to be involved
- Proceed after presenting (no user confirmation needed — this is a code-only check)
Phase 3: Gather Context
Before checking any logic, collect the full picture for the batch's feature area:
- Read all source files relevant to the batch
- Trace the data flow for the feature area end-to-end
- Note dependencies, shared state, API contracts, and external integrations
- Read existing tests for the relevant code — they reveal intent and edge cases
- Check the Covers field on each test case to identify which backlog stories are involved
- Read the story acceptance criteria from the relevant epic/backlog file
Do NOT proceed to logic checks until you have the full picture.
Phase 4: Code Logic Check (per case)
For each case in the batch:
- Read the test case steps and acceptance criteria carefully
- Trace each step through the actual source code
- For each acceptance criterion, verify:
- The code path exists and is reachable
- Conditionals are correct (no off-by-one, no inverted logic)
- Data flows correctly between components
- Error handling covers the expected failure modes
- Edge cases mentioned in the test case are handled
- Assign a verdict with confidence (high = full code path traced, medium = partial trace or complex logic, low = inference without full trace):
- Pass (high/medium/low) — logic is correct, code handles the scenario properly
- Warning (high/medium/low) — potential issue found, describe with file:line reference
- Fail (high/medium/low) — confirmed broken, describe with file:line reference and root cause
Phase 5: Resolve Issues
For every Warning or Fail verdict, classify and act. Read references/issue-classification.md for the full classification guide (quick fix vs design gap).
Phase 6: Update Tracking
Per-case: Update the UAT tracking file
For each case in the batch:
- Check the Claude Sense Check checkbox:
- [x] Logic verified from code perspective - Fill in the Notes line with verdict and what was checked or fixed:
- Pass:
"Pass (high) — verified [what was checked], code handles [scenario] correctly" - Fixed:
"Fixed (high) — [issue description], resolved in [commit-hash]" - Design gap:
"Warning (medium) -> [story-id] — [gap description], backlog story created"
- Pass:
Per-area: Update UAT index
After updating the tracking file, update any status summary tables to reflect the new sense-check counts.
Phase 7: Report & Hand Off
Output a summary:
### Claude Sense Check Complete
**Batch:** UAT-### to UAT-### ([area name])
**Results:**
| Case | Title | Verdict | Confidence | Notes |
| ---- | ----- | ------- | ---------- | ----- |
| UAT-### | [title] | Pass/Warning/Fixed | high/medium/low | [one-line summary] |
**Fixes Applied:** [count]
- [commit-hash]: [one-line description] (for UAT-###)
**Backlog Stories Created:** [count]
- [story-id]: [one-line description] (for UAT-###)
**Progress:** [x]/[total] UAT cases sense-checked
**Remaining:** [count] cases unchecked
**Suggested Next Batch:** UAT-### to UAT-### ([area name]) — [why]Include a YAML block for machine-parseable results:
sense_check:
batch: [UAT-###, UAT-###]
area: "[area name]"
results:
- id: UAT-###
verdict: pass
confidence: high
notes: "[one-line]"
fixes: 0
stories_created: 0
progress: "X/Y"Rules
- Never re-check an already checked case
- Never check more than 5 cases in one run — stay focused
- Always update the tracking file before finishing — the checkboxes are the source of truth
- Always gather full context before starting logic checks — no guessing
- Always use
/story-cyclefor fixes — maintain TDD discipline - Follow coding standards in
docs/reference/CODING_STANDARDS.md - Follow verification rules: run the project's test command before claiming fixes are complete
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

