SKILLEMALL.ai
GitHub ↗ RU Sign in

CC reflection-coach

Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.

paperclipai/paperclip Agent Skills author: paperclipai MIT 1 file body ≈ 2 877 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change.

As a process C 58/100 · Has gaps — References files that are not bundled: /PAP/issues/PAP-NNN, /PAP/issues/PAP-MMM, /PAP/issues/PAP-XXX

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
82/100
safety, quality, tests
Safety 60%
90
Quality 40%
70
Run on models
none yet
Process rating
C
58/100
Has gaps
References files that are not bundled: /PAP/issues/PAP-NNN, /PAP/issues/PAP-MMM, /PAP/issues/PAP-XXX
Tools and files w 18
0
Progress reporting w 2
0
Result and completion w 14
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-credential-use SKILL.md:80
    Credential used in a network call (verify the destination is the intended service)
    curl -sS "$PAPERCLIP_API_URL/api/issues/<issueId>" -H "Authorization: Bearer $PAPERCLIP_API_KEY"
  • medium Exfiltration net-credential-use SKILL.md:81
    Credential used in a network call (verify the destination is the intended service)
    curl -sS "$PAPERCLIP_API_URL/api/issues/<issueId>/comments" -H "Authorization: Bearer $PAPERCLIP_API_KEY"

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: /PAP/issues/PAP-NNN
  • warning missing-ref reference to a missing file: /PAP/issues/PAP-MMM
  • warning missing-ref reference to a missing file: /PAP/issues/PAP-XXX
  • warning missing-ref reference to a missing file: /PAP/issues/PAP-YYY
  • note frontmatter-key unknown frontmatter key "key"
  • note frontmatter-key unknown frontmatter key "recommendedForRoles"

Process rating: all ten parameters 58/100

Will not run. References files that are not bundled: /PAP/issues/PAP-NNN, /PAP/issues/PAP-MMM, /PAP/issues/PAP-XXX
  • 0Tools and files. 4 referenced file(s) missing: /PAP/issues/PAP-NNN, /PAP/issues/PAP-MMM, /PAP/issues/PAP-XXX
  • 0Progress reporting. Says nothing while it works
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 60 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2877 tokens
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (8 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 192: enough signal without eating the budget
  • +4Structure: 18 headings
  • +3Step-by-step instructions: 60 items
  • +4Has examples (5 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.