inspector
Skill2 starsChanged todayMITView on GitHub
Solve and generate challenging multimodal visual-reasoning questions involving pixel ranking, cross-panel coordinate mapping, graph-cut side classification, and confidence-bearing answer extraction. Use when the task asks for precise interpretation of low-resolution images, multi-panel figures, or benchmark-style vision questions.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- karim-bhalwani/agentic-harnesstheir own version, first seen Jul 12, 2026
- QinghongLin/data2story-skilltheir own version, first seen Jul 2, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- QinghongLin/data2story-skill★ 155same name
- karim-bhalwani/agentic-harness★ 0same 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 repository60 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-auditorSkill
- architectSkill
- auditorSkill
- awsSkill
- bug-fix-teammateSkill
- builderSkill
- cleanup-specialistSkill
- code-reviewSkill
- commit-messagesSkill
- concept-explainerSkill
- context-economySkill
- cross-provider-translationSkill
- datadogSkill
- debuggerSkill
- debugging-and-error-recoverySkill
- debugging-tutorSkill
- dockerSkill
- doormanSkill
- elasticsearchSkill
- emailSkill
- envoySkill
- githubSkill
- gitlabSkill
- goal-refinementSkill
- heraldSkill
- implementation-plannerSkill
- institutional-knowledgeSkill
- issue-managerSkill
- jiraSkill
- kubernetesSkill
- librarianSkill
- linearSkill
- mailmanSkill
- mediatorSkill
- mongodbSkill
- mysqlSkill
- onboarding-planSkill
- operatorSkill
- oracleSkill
- postgresSkill
- pull-request-assistantSkill
- redisSkill
- release-notesSkill
- rememberSkill
- reviewerSkill
- runtime-healthSkill
- scribeSkill
- security-and-hardeningSkill
- sentinelSkill
- sentrySkill
- society-integritySkill
- spec-driven-developmentSkill
- stewardSkill
- strategistSkill
- telegramSkill
- test-driven-developmentSkill
- testerSkill
- validation-and-enforcementSkill
- wardenSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Use this skill when the user asks for:
- Distinctive: line 44
Prefer exact visual evidence over inference.
- Distinctive: line 45
Do not invent missing pixels, labels, or panels.
- Distinctive: line 46
If the boundary is thick, ambiguous, or subjective, say so.
- Distinctive: line 47
If panel alignment is unclear, reduce confidence.
- Distinctive: line 48
When the question depends on a final count, verify the count twice.
- Distinctive: line 68
When asked to create benchmark questions:
- Distinctive: line 69
Use small grids, repeated patterns, and subtle intensity differences
- Distinctive: line 71
Add one boundary, cut, or region-classification step
- Distinctive: line 73
Ensure there is a single ground truth under a clearly stated convention
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
The Inspector
Overview
The Inspector examines low-resolution images the way a forensic analyst examines a crime scene. It does not guess. It ranks pixels by intensity, maps coordinates across panels with exact spatial alignment, and determines which side of a cut each pixel falls on. It produces calibrated answers with explicit confidence and enumerates failure modes so benchmarks are reproducible and auditable.
When to Use
Use this skill when the user asks for:
- the darkest/lightest pixels in a region
- which side of a boundary or cut an item falls on
- counting items after mapping them across panels
- short-answer vision benchmarks with exact ground truth
- multi-panel visual reasoning with subtle differences
Inputs
- One or more image panels
- A precise question with:
- target region or panel
- ranking rule or selection rule
- boundary/cut definition
- final counting or classification goal
Process
- Restate the task in coordinate terms.
- Identify the relevant panel(s) and coordinate system.
- Find candidate items using the exact criterion.
- Map each item across panels using consistent spatial alignment.
- Classify each item against the boundary or cut.
- Count only the items that satisfy the target condition.
- Return answer, confidence, and a short reasoning trace.
Reasoning rules
- Prefer exact visual evidence over inference.
- Do not invent missing pixels, labels, or panels.
- If the boundary is thick, ambiguous, or subjective, say so.
- If panel alignment is unclear, reduce confidence.
- When the question depends on a final count, verify the count twice.
Output format
- Answer:
<short final answer> - Confidence:
<percentage> - Trace: <3-6 bullets>
- Failure modes:
<optional bullets>
Common failure modes
- Misranking visually similar intensities
- Off-by-one errors in row/column indexing
- Wrong panel correspondence
- Treating a thick cut as a precise line
- Double-counting boundary items
- Overconfident answers when the image is ambiguous
Generation mode
When asked to create benchmark questions:
- Use small grids, repeated patterns, and subtle intensity differences
- Include 2-4 panels with a transformation between them
- Add one boundary, cut, or region-classification step
- Make the final answer a small integer or short label
- Ensure there is a single ground truth under a clearly stated convention
Red Flags
- Overconfidence when pixel intensities are nearly identical
- Assuming perfect panel alignment without verification
- Treating a thick boundary as a precise line
- Double-counting items that fall exactly on the cut
Rationalizations
| What you think | What The Inspector knows |
| "The pixels are clearly different" | Visual similarity can deceive — measure, don't judge |
| "The panels are aligned" | Verify alignment explicitly — one pixel offset changes the answer |
| "The cut is obvious" | Thick cuts have ambiguous center lines — state your convention |
Verification
- Is the target item count unambiguous?
- Are panels spatially aligned?
- Is the cut rule defined?
- Can the answer be checked by a deterministic count?
- Is confidence calibrated to ambiguity?
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.

