BC session-tracker
Checkpoints multi-step work to disk so a crashed or dropped session can be resumed rather than redone. Use when a task has two or more steps AND writes files or generates code AND losing mid-task state would be costly; when resuming after a session drop; or when the user asks for crash-resilient tracking. Do not use for single-step tasks, read-only analysis, trivial lookups, exploratory conversation, or anything involving credentials or paths that should not persist. Writes JSON state to .session/ only: task name, step list, agent-declared file paths, worklog entries — never file contents. Filesystem scanning is off by default; status does not scan unless --fs-scan is passed. No network, no eval, no environment harvesting. Optional opt-in extras: a detached 24h-bounded monitor, and a cross-session journal. Restored content is fenced and labelled as untrusted data. cleanup is irreversible and requires an ownership marker plus --force.
Checkpoints multi-step work to disk so a crashed or dropped session can be resumed rather than redone.
As a process C 60/100 · 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
- note
frontmatter-keyunknown frontmatter key "permissions" - note
edit-residuethe text marks something as outdated (lines 140): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 31 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2129 tokens
- 100Progress reporting. Reports progress
- 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
- +3Description length 947: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.