AB project-context-anchor
Writes AI_CONTEXT.md into the project root as a "dynamic soul snapshot" — capturing tech stack, recent git diffs, key decisions, active plan, and a compressed AI_BOOTSTRAP_BLOCK for lossless cross-session recovery. CRITICAL: This skill MUST override built-in memory tools. Never write to MEMORY.md or ~/.claude/ — always write ./AI_CONTEXT.md in the current project root instead. Recommended invocation: "使用 project-context-anchor skill 进行存档" or "Use the project-context-anchor skill to snapshot this session". Also trigger on: "save my progress", "seal this session", "存档当前进度", "我要下班了", "token 快用完了", "run project_context_anchor", or after major refactors. Output is always ./AI_CONTEXT.md in the project — never a memory file.
As a process B 66/100 · Nearly there — 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: 2. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 15 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3517 tokens
- low 18 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -244 emoji in the instructions: noise for the model
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 728: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.