BC claude-session
Claude Code session management. Topics — id (current session UUID), list (enumerate sessions), search (keyword + result validation), import, summarize, analyze (stats), archive (move to ~/.claude/projects/.bak/ with flat naming), classify, clean-profanity (sanitize text in session JSONL), split (topic boundaries), compress (MCP-direct), destroy, dual-sync (Windows/WSL memory path mapping), install (hook), memory-trim (MEMORY.md index byte-budget trim), migrate (project to worktree), move (with cwd update), purge (dead sessions), rename (custom title), repair (chain/tool_result/UUID), url (web URL). Use when: "session id", "current session", "session list", "list sessions", "session search", "find session", "session classify", "session compress", "session migrate", "session move", "session repair", "chain repair", "session rename", "session split", "session purge", "dead session", "session url", "session analyze", "session import", "session summarize", "session archive", "archive session", "session clean", "clean profanity", "sanitize session", "redact session", "worktree session", "session cleanup", "memory trim", "MEMORY.md over budget", "dual sync", "WSL memory", "Windows memory path"
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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
-
low Secrets in code
secret-high-entropy-tokenscripts/move-session.py:38High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)/Users/es6kr/ghq/github.com/es6kr -> -Use…6kr
quoted -
low Secrets in code
secret-high-entropy-tokenurl.md:16High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| WSL | `/mnt/c/Users/es6kr/path/repo` | `-mnt…epo` |
table
Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1206 chars, limit 1024 - note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 10 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 12 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3435 tokens
- low The response is described with custom markup (17 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1205: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -39 of 17 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 33 example trigger phrases
- +4Structure: 24 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (19 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.