BD read-claude-code-history
Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file recovery from transcripts, and which session ran a given command in a known time window. Use when the user asks what was said, wants a session ID or original context, needs proof of what a session contained, or needs past-session runtime evidence about commands, tool calls and hook runs — query this index instead of raw-scanning transcript files. Not for Codex (use read-codex-history); with no platform or several named, start at local-conversation-history.
Reads, searches and exports local Claude Code and Kimi CLI history without resuming work: timelines, verbatim user input, keyword or fuzzy recall, file…
As a process D 46/100 · Unfinished process — References files that are not bundled: scripts/**/*.py
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6835 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/**/*.py - note
edit-residuethe text marks something as outdated (lines 367, 374, 433): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: scripts/**/*.py
- 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. 7 mutating operations with no state check
- 60Failures and branches. 2 branches
- 70Execution cost. Instruction body is 6835 tokens
- 100Steps. 24 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (17 tags): a typed call is more reliable
- medium 6 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 612: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 9 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.