BB who-is-actor
This skill should be used ONLY when the user EXPLICITLY and UNAMBIGUOUSLY requests a Git repository commit-history analysis that produces aggregate collaboration-pattern metrics (commit cadence, churn, rework signals, conventional-commit compliance, bus-factor risk). The skill is scoped to repository-level technical analysis. It is NOT a performance-management, HR, ranking, or personnel-evaluation tool, and agents MUST refuse to use its output for those purposes. The report produces NO contributor display names at all: author names are read by local pipelines only to compute aggregate counts (e.g. distinct-author count per file for bus-factor risk) and are discarded locally before any data leaves the host. Activation requires an explicit, opt-in user request that BOTH (a) states a clear analyze-this-Git-repository intent AND (b) supplies a concrete repository path (or unambiguous repo reference). Generic conversational mentions of "analyze repository", "profile developers", "commit habits", "developer report card", "code quality", "team efficiency", "work habits", "engagement", "代码分析", "研发效率", "开发者画像", "提交习惯", "工作习惯", or "参与度" WITHOUT a repository path or explicit "analyze this Git repository" framing are NOT sufficient to activate this skill. In that situation the agent MUST first (1) confirm the user actually wants to run repository profiling, (2) request a concrete repository path, (3) confirm the user has authority to analyze that repository, (4) remind the user that other contributors' Git metadata will be processed, and (5) recommend Dry-Run preview — only after these are resolved may any git command be executed. Activation phrases (must include an explicit analyze-this-repo intent AND a repository path or unambiguous repo reference): "analyze the git repository at <path>", "run who-is-actor on <path>", "generate a repository-level collaboration-pattern report for <path>", "分析仓库 <path>", "对 <path> 这个 git 仓库生成仓库级协作模式报告". Privacy & data-handling: relies purely o
As a process B 69/100 · Nearly there — weak spots: result and completion, execution cost
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 2651 chars, limit 1024 - warning
body-longSKILL.md body ≈ 11982 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 2651 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 11982 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 18 branches
- 100Steps. 128 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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 (6 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 2650: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -224 emoji in the instructions: noise for the model
- +2Single-language instructions
- +5Description quotes 15 example trigger phrases
- +4Structure: 44 headings
- +3Step-by-step instructions: 128 items
- +4Has examples (17 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.