AC back-to-the-chronicle
Reconstruct a project’s missing founding or historical Chronicle from project-related Codex and Claude session JSONLs, automatic traces, Git history, controller ledgers, receipts, artifacts, and external-state readbacks. Use when asked to backfill a Chronicle, recover the full story, explain how a project reached its current state, create an initial Chronicle for an existing project, recover dead ends or abandoned experiments, or turn fragmented Claude/Codex/human work into an evidence-anchored operational history. Compose the Chronicle skill and preserve strict witnessed, artifact-measured, and inferred-intent boundaries.
Reconstruct a project’s missing founding or historical Chronicle from project-related Codex and Claude session JSONLs, automatic traces, Git history…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 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
- 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 Concealment
en-hide-from-userreferences/chronicle-compatibility.md:5Instruction to hide actions from the user (documentation of a security skill)silently install Chronicle. Inventory and manifest validation work without it.
security skill
Files scanned: 17. 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 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 42 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2097 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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
- -33 of 6 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 630: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.