FF skill-compass
Evaluate skill quality, find the weakest dimension, and apply directed improvements. Also tracks usage to spot idle or risky skills. Use when: first session after install, or user asks about skill quality, evaluation, inbox, suggestions, or improvement.
As a process F 54/100 · Will not run — References files that are not bundled: scripts/hud-extra.js
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- The text references files that are not there: add them or drop the references.
- 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 · 9
-
critical Secrets in code
secret-anthropic-keyprompts/d3-security.md:284Anthropic API key (quoted — discussed, not commanded)API_KEY = "sk-a…789"
quoted -
critical Secrets in code
secret-anthropic-keyprompts/d3-security.md:307Anthropic API key (quoted — discussed, not commanded)"description": "Hardcoded Anthropic API key: sk-a…789",
quoted -
high Concealment
en-hide-from-userSKILL.md:56Instruction to hide actions from the userSilently run skill discovery (scan immediate children `*/SKILL.md` in each skill root — same as `/setup` Step 3, do NOT recurse) and D1+D2+D3 quick scan on all discovered skills. Save `setup-state.jso
Medium and low: 6
-
medium Secrets in code
secret-labelled-tokenprompts/d3-security.md:284Labelled token / key literal (vendor format unknown — verify it is not a live credential)API_KEY = "sk-a…789"
-
low Risky intent
intent-offensive-securityprompts/d3-security.md:72Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### 3. File System Privilege Escalation
-
low Risky intent
intent-offensive-securityprompts/d3-security.md:164Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| High | Privilege escalation, excessive permissions | -3 per finding |
-
low Secrets in code
secret-password-literalprompts/d3-security.md:284Hard-coded password / key literal (may be an example)API_KEY = "sk-a…789"
-
low Secrets in code
secret-labelled-tokenprompts/d3-security.md:307Labelled token / key literal (vendor format unknown — verify it is not a live credential) (quoted — discussed, not commanded)"description": "Hardcoded Anthropic API key: sk-a…789",
quoted -
low Risky intent
intent-offensive-securityshared/tool-instructions.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **File system privilege escalation** — access outside expected scope
Files scanned: 62. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/hud-extra.js - note
frontmatter-keyunknown frontmatter key "commands"
Process rating: all ten parameters 54/100
- 0Tools and files. 1 referenced file(s) missing: scripts/hud-extra.js
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 59 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3476 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 10 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +3Description length 253: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.