Use when bootstrapping or tightening the smallest harness-oriented skill from an existing repository, workflow, evaluation corpus, or harness-analysis chain. Trigger for meta skills, reusable harness workflows, Qoder/Codex plugin skill sets, skill blueprints, and harness-analysis-like skills that need evidence-backed references, validation gates, and qodercli forward-tests.
SkillScore77Maintained
Automatic
◆AI Engineer pack
Last verified 8/13/2026
What it changes
Passed 15 of 20 test cases with the skill, and 8 of 20 without it.
Without skill41%
With skill77%
Checks it passed that the model alone missed
Omits tool-call markup and shell probes.
Plugin wrapper paths use .agents/skills/.
Returns status value insufficient-evidence.
and 6 more in the full report
8 fixed9 passed either way5 still failing0 broke
Pass-rate lift
+36 pp
Tokens
-3%
Agent turns
0%
Response time
-49%
Model gemini-3.6-flashMeasured 8/13/2026v117 of 22 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
During a forward-test run where no tools or file attachments are provided, what status value must be emitted in the skill map?
What was checked, without and with the skill
Checked
Without skill
With skill
Returns status value insufficient-evidence.
Missed
Passed
case-14 · gemini-3.6-flash · 8/13/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md58 lines2 files
Harness Skill Creator
Create the smallest skill that makes another agent repeat one harness job with
evidence, validation, and clear ownership.
Workflow
Resolve source, target, and host: canonical skills/<name>/, .agents/skills/ wrapper, or both.
Inspect the source chain before designing: entry SKILL.md, first-hop
references, scripts, validators, templates, specs, tests, plugin manifests,
and any real smoke evidence.
Load references/bootstrap-patterns.md after the first inventory. Use it to
extract patterns, not product-specific rules.
Draft the minimum viable skill map:
skill name and trigger sentence
one job the skill owns
files to create under skills/<skill-name>/, usually SKILL.md plus one reference
evidence boundary and validation commands
forward-test prompt and pass/fail gates
Initialize new canonical skills with the system skill-creator helper when
available. Add scripts/ only for stable repeated automation; keep ad-hoc
evaluation prompts out of runtime scripts.
Write the SKILL.md as a router. Put trigger conditions in frontmatter
description, keep the body short, and route detailed rules to first-hop
references.
Validate locally, then forward-test. Treat qodercli output as model evidence;
local validators and file inspection decide pass/fail.
Design Gates
Prefer one skill over a stage tree until the target process proves multiple
reusable stages.
Copy ownership shape, not product names, branch policy, private commands, or
source-specific team routing.
Keep .agents/skills/ as a wrapper or mirror when the workflow is shared by
the plugin; canonical judgment belongs under root skills/.
Do not add install, network, server, migration, or dependency-changing
commands unless the user requested them and source evidence supports them.
Prefer portable Node/Python validators or target-owned commands. Do not default generated validation gates to Unix-only grep/find checks.
In attachment-only or no-tools forward-tests, never emit tool-call markup, shell probes, or inspection plans; return the skill map with status: "insufficient-evidence" when needed.