makes the work
The worker
not present
No work step here. This is probably a skill that reads or coordinates, not one that produces something.
drop another
.md file to compare - side-by-side diff against contract-test
contract-test
Checks that connected services still behave the way your work expects.
description: "Triggers on prompt mention of 'contract-test'."What it does for you
Checks that connected services still behave the way your work expects.
What it produces
A recent result, so you can see the kind of work it returns.
loading…
How to get it
These run inside the Snappy workspace. Want this working in your business? I set skills like this up with you, in one focused week.
For developers how this skill is built, graded, and how it runs
at a glance- the short version
eval modemanual
categoryOps
stages1
what's inside - the parts that make up a skill 2/4 present
A skill is just a few plain-text files. Only the main one is required. The rest are optional, added as the work needs them. This is what the skill is made of; how it runs is just below.
The skill
state/skills/contract-test/SKILL.md
present
the skill itself, in plain text
The main file. It says what the skill is and lays out the steps in plain English.
Code
state/lib/contract-test.ts
not present
code the skill can run
Optional. Many skills are just words and need no code at all.
Scripts
state/bin/contract-test/
not present
helper scripts
Optional. Added when a skill has a few commands to run.
Loader
state/skills/contract-test/AGENTS.md
present
what the AI loads on the fly
Loaded automatically the moment this skill is needed. Kept short on purpose.
how it's graded - what counts as a good run 3 criteria · 1 deterministic · 2 judge
Each row is one thing a good run has to get right. deterministic means a quick check decides, pass or fail. judge means the AI reads the result and rates it. Grading each piece on its own (instead of one overall score) shows exactly where a run fell short, so the fix is obvious.
name
kind
check
skill_is_dormant
deterministic
The 'graduation' field in SKILL.md is set to 'dormant'.
description_mentions_reclamation
judge
The skill's description clearly states it was reclaimed and is a stub for historical eval rows.
no_new_runs_expected
judge
The eval section explicitly states 'No new runs expected'.
how it runs - the shared frame every skill uses 3/5 present
Every skill runs the same way. One part does the work, a separate part checks it, and a short loader hands the AI exactly what it needs for the job. Anything this skill doesn't use shows a one-line note saying why, on purpose, not by accident.
checks the work
The reviewer
present
Robert (weekly review)
No automatic check. Robert reviews these by hand. The part that made it still isn't the part that approves it.
frame
learns
Self-correction
not present
This skill doesn't fix its own gaps yet.
tidies up
Background fixes
present
queued for rewrite
Bigger fixes that can't be made on the spot get queued and rewritten in the background later.
remembers
Run history
present
state/log/evals.ndjson Every run is written down here, so the next time this skill is used it already knows how the last runs went.
Critical rules
the things this skill must not get wrong
- NEVER treat a dormant skill as runnable without reviving its spec
- ALWAYS prefer an existing active skill over resurrecting a dormant one
what it has learned - fixes written back in over time sample
When a run hits something this skill didn't handle, the fix gets written back into the skill so it doesn't happen again. FIXED means it was corrected on the spot. LOGGED means it's queued for a bigger rewrite. Either way, the skill gets a little better and never makes the same mistake twice.
- Loading feedback rows…
how the work flows- step by step
1
data
eval log
`state/log/evals.ndjson` (skill: "contract-test" - historical only)
SKILL.md- the skill, written out in plain English
contract-test
Reclaimed by state/bin/orphan-audit/fix.ts on 2026-04-18. Historical eval rows exist under this name (count at reclaim: 336) but no prose doc was on disk. This stub gives those rows a catalog home so lint stops flagging them as ghosts.
Eval
Dormant. No new runs expected.
Rubric
criteria:
- name: skill_is_dormant
kind: deterministic
check: "The 'graduation' field in SKILL.md is set to 'dormant'."
- name: description_mentions_reclamation
kind: judge
check: "The skill's description clearly states it was reclaimed and is a stub for historical eval rows."
- name: no_new_runs_expected
kind: judge
check: "The eval section explicitly states 'No new runs expected'."AGENTS.md- what the AI loads when this skill comes up
contract-test - loader (dormant)
Full reference: state/skills/contract-test/SKILL.md. This skill is dormant; new runs are not expected.
Critical Rules
- NEVER treat a dormant skill as runnable without reviving its spec
- ALWAYS prefer an existing active skill over resurrecting a dormant one
Commands
| ui model | live composition via compose_inline, persisted as artifact lang_body, reopened with OpenArtifact | |full spec: state/skills/contract-test/SKILL.md |eval log: state/log/evals.ndjson (skill: "contract-test" - historical only)
Known Pitfalls
_(reclaimed ghost - no failures recorded in the new catalog yet.)_
Self-Test
- [ ] Is this skill truly needed, or should I use an active neighbor?
Found a gap? Edit this file. <!-- footer-injection-point -->
api.ts- the code it can call
⚠ no api.ts - this skill has no typed action surface
scripts- helper scripts it can run
prose-only skill - 1 inline code block live in SKILL.md above (no state/bin/ sidecar yet).
how we check it- the checks, plus the last 10 runs
rubric
manual
manual Robert review - no automated rubric
recent
no runs
actor/auditor: unverifiable
deps
none declared
no recent runs logged - the eval contract is declared but nothing has been graded yet