AC session-recovery
Recover lost agent session content and file changes from on-disk conversation logs. Streaming and OOM-safe on 700MB+ daily JSONL. Two commands: search.py for keyword search across recent sessions (with hit snippets, file-op listing, JSON for agent consumption); extract.py for pulling full write/edit content from a single session by ID prefix, with optional replay-rebuild for pure-edit sequences and safe restore-to-disk (refuses silent overwrites without --yes). Multi-agent aware via --agent main|all|a,b. Configurable data root via --root flag or SESSION_RECOVERY_ROOT env var (default ~/.openclaw/agents/). Trigger when user wants to find lost session content, recover files written by an agent, locate which session modified a file, search session history by keyword, or rebuild a file from an edit replay. Also triggers on 找回会话, 会话被覆盖, 历史会话搜索, 文件被删了, session 丢了, 找回某个文件, 重放编辑.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 988 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)
- +3Description length 884: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.