manual-test-plan
Skill0 starsChanged 29 days agoMITView on GitHub
Generate a full manual testing plan from the changes on the current branch. Asks which tools are available (browser, API client, CLI, DB, events/queues, logs), then writes a per-step plan with literal expected outputs — JSON payloads, log lines, event bodies, exit codes. Use when the user says "make a test plan", "manual testing plan", "how do I test these changes", or before shipping a branch that needs QA verification.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- renzrollon/interlocktheir own version, first seen Nov 5, 2026
- ProxiBlue/claude-skillstheir own version, first seen Oct 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- renzrollon/interlock★ 62same name
- ProxiBlue/claude-skills★ 18same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- .codex/AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- animate-expoSkill
- animateSkill
- break-uiSkill
- claritySkill
- code-reviewSkill
- code-simplificationSkill
- diagnoseSkill
- grill-with-docsSkill
- idea-refineSkill
- improve-codebase-architectureSkill
- incremental-implementationSkill
- interactive-test-planSkill
- planning-and-task-breakdownSkill
- review-animationsSkill
- security-and-hardeningSkill
- spec-driven-developmentSkill
- tddSkill
- write-a-skillSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Follow phases in order. Do not skip.
- Distinctive: line 16
Ask which scope to plan against:
- Distinctive: line 23
Wait for the answer.
- Distinctive: line 29
Test-surface signals: new routes, new env vars, new migrations, new/changed events, changed validation, modified auth, new feature flags, …
- Distinctive: line 34
Ask which tools are available.
- Very specific: line 54
Ask for output path. Suggest defaults based on what exists in the repo (./testing-plans/<branch>.md, ./docs/testing/<branch>.md, …
- Very specific: line 87
If the expected output cannot be determined from the diff alone, write Expected output: TBD — confirm with developer.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Manual Test Plan
Generate a manual testing plan grounded in the actual diff on the current branch. Output is a single markdown file a QA engineer can execute without asking the developer questions.
Workflow
Follow phases in order. Do not skip.
Phase 1 — Ask change scope
Ask which scope to plan against:
- Branch diff vs main (
git diff main...HEAD) - Uncommitted changes only (staged + unstaged)
- Branch + uncommitted
- Specific commit range (
<base>..<head>) - Last commit (
git diff HEAD~1..HEAD)
Wait for the answer.
Phase 2 — Read the diff (delegate to reader)
Delegate to the reader agent. Pass the exact git command. Ask for:
- One-line summary per changed file (new endpoint, modified schema, added migration, etc.)
- Test-surface signals: new routes, new env vars, new migrations, new/changed events, changed validation, modified auth, new feature flags, new CLI flags, modified response shapes
- Structured summary under 400 words — never raw diff
Phase 3 — Ask about tools
Ask which tools are available. Default catalog:
- Browser + DevTools
- API client (curl / Postman / HTTPie / Bruno — which?)
- CLI / shell (which binaries?)
- Database client (psql / mysql / TablePlus — which DB?)
- Event/queue inspector (Kafka UI / SQS console / webhook.site / ngrok)
- Logs / observability (tail / Datadog / Grafana / Sentry)
- Anything else? — catch project-specific tools (Stripe CLI, AWS CLI, kubectl, flag dashboards)
Phase 4 — Clarify ambiguous test surfaces
Based on the diff summary, ask 1–4 targeted questions only where the plan would otherwise be wrong. Skip if the diff is self-explanatory.
Examples:
- "The new
/refundendpoint readscustomer.tier— test free-tier and paid-tier, or only one?" - "Migration adds NOT NULL column with default — include backfill verification?"
- "Event
OrderShippedwas renamed — which consumers need re-verification?"
Phase 5 — Ask save path
Ask for output path. Suggest defaults based on what exists in the repo (./testing-plans/<branch>.md, ./docs/testing/<branch>.md, tmp/test-plan-<branch>.md). Do not write until confirmed.
Phase 6 — Generate the plan
Required sections:
- Header — branch, base commit, date, 1-paragraph change summary
- Prerequisites / setup (always) — env vars, feature flags, seed data, services to start, accounts/roles, migrations, fixtures
- Test sections, one per logical change area, each containing:
- Happy path — main intended flow
- Edge cases — boundaries, empty/null, large inputs, concurrency
- Negative cases — invalid inputs, auth failures, expected errors
- Regression checks — adjacent untouched features the changed code touches
- Cleanup / teardown — reset state, remove test data, disable flags
Each step uses:
#### Step N.M — <short title>
**Tool:** <browser | curl | psql | kafka-ui | ...>
**Action:**
<exact command, click sequence, or request payload>
**Expected output:**
```<json|text|sql|log>
<literal expected output — actual JSON body, log line, row count, exit code, event payload>
```
**Pass criteria:** <what must match for this step to pass>Non-deterministic values (timestamps, IDs) use placeholders: <ISO-8601 timestamp>, <UUID> — never literal example values that could be mistaken for required matches.
If the expected output cannot be determined from the diff alone, write **Expected output:** TBD — confirm with developer. Do not invent.
Phase 7 — Write and confirm
Delegate the file write to the implementer agent with the filled-in plan. Then report:
- Path written
- Number of test steps
- Any sections marked TBD
Quality bar
A QA engineer who has never seen this code must be able to execute the plan without asking the developer questions. "Verify the response looks correct" is a failure — show the exact expected payload.
Delegation
- Phase 2 (diff reading) →
readeragent - Phase 6 file write →
implementeragent - Phases 1, 3, 4, 5, 7 → main agent (user interaction / judgment)
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.

