AC gitrakz
Drive a self-hosted gitrakz instance — the tool that syncs a GitHub user's activity into local SQLite, renders a filterable timeline and derived work sessions, and runs deterministic programmatic templates that export to CSV/PDF/JSON. Install or run it with Docker, then query its bearer-protected REST API under /api/v1 (owners, repos, timeline, sessions, sync + sync status, templates CRUD, LLM template generation, run, export) — or drive the same capabilities as MCP tools over streamable HTTP (/mcp) or stdio (`gitrakz mcp`). Use when the user wants to set up gitrakz, trigger or check a GitHub activity sync, pull a timeline or work-sessions timesheet, or run and export a template.
Drive a self-hosted gitrakz instance — the tool that syncs a GitHub user's activity into local SQLite, renders a filterable timeline and derived work…
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Dangerous commands
cmd-privilegereferences/setup.md:40Privilege escalation / world-writable permissionssudo bash gitrakz-install.sh --system
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 85Steps. 35 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1800 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 688: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.