BC safe-merge-update
Safely merge upstream OpenClaw updates without destroying plugin/skill injections, custom UI tabs, or workspace features. Two-phase: Phase 1 (automated) merges, builds, and restarts the gateway from a safe-merge branch — without touching local-desktop-main. Phase 2 (user-confirmed) promotes to local-desktop-main and pushes to the fork remote only after the user verifies the gateway is healthy.
As a process C 55/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7200 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 57 mutating operations with no state check
- 40Consistency. Frontmatter name (safe-merge-update) differs from the folder (safe-update-merge)
- 60Tools and files. Uses tools (bash, web, git, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7200 tokens
- 100Steps. 156 steps
- 100Failures and branches. 5 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -220 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 396: enough signal without eating the budget
- +4Structure: 52 headings
- +3Step-by-step instructions: 156 items
- +4Has examples (10 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.