OR Key
drop another .md file to compare - side-by-side diff against snappy-resume

snappy-resume

Resumes a helper you paused so it picks back up.
description: "Triggers on prompt mention of 'snappy-resume'."
personal 2 files
Export

What it does for you

Resumes a helper you paused so it picks back up.

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.

Work with me
For developers how this skill is built, graded, and how it runs

at a glance- the short version

eval modeauto-shape
categoryOps
stages2

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/snappy-resume/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/snappy-resume.ts not present
code the skill can run
Optional. Many skills are just words and need no code at all.
Scripts
state/bin/snappy-resume/ not present
helper scripts
Optional. Added when a skill has a few commands to run.
Loader
state/skills/snappy-resume/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 · 2 deterministic · 1 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
agent_status_updated
deterministic
The 'status' field in 'state/agents/<name>.json' is 'running' after skill execution.
log_entry_created
deterministic
A log entry with 'action:\"resume\"' and 'id:<name>' is present in 'state/log/agents.ndjson' after skill execution.
correct_tick_headroom_quoted
judge
The operator message correctly quotes the 'ticks/max_ticks' value for the agent as per 'state/agents/<name>.json'.

how it runs - the shared frame every skill uses 2/5 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.

makes the work The worker
inferred
see `state/skills/snappy-resume/SKILL.md` Steps from the run command
No worker is named directly, so the command this skill runs is treated as the worker.
checks the work The reviewer
inferred
shape gate an automatic check
The check is an automatic pass or fail on the shape of the result, run separately from the work itself.
frame
learns Self-correction
not present

This skill doesn't fix its own gaps yet.

tidies up Background fixes
present
queued for rewrite runs in the background
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 unknown runs
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
  1. Idempotent: resuming an already-running agent is a no-op pass.

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.

  1. Loading feedback rows…

how the work flows- step by step

1 generator
invoke
see `state/skills/snappy-resume/SKILL.md` Steps section
+ eval for this step
→
2 data
eval log
`state/log/evals.ndjson` (skill: "snappy-resume")
+ eval for this step

SKILL.md- the skill, written out in plain English

snappy-resume

One job: flip a paused agent's status back to running so the 10-min cron tick starts firing for it again.

Usage

/snappy-resume                 # resumes "default"
/snappy-resume verify-loop     # resumes the named agent

Steps

  1. Resolve name: first argument if present, else default.
  2. Run:
   bash ~/projects/snappy-os/state/bin/agents/resume.sh <name>
  1. Confirm state/agents/<name>.json has status=running.
  2. Tell the operator the agent is running again, quote ticks/max_ticks

so they know how much headroom remains.

Why

Paired with /snappy-pause. Keeps the agent file + prompt + tick count intact across the halt.

Eval

Shape-gate:

  • state/agents/<name>.json has status=running after invocation.
  • state/log/agents.ndjson gained a {action:"resume", id:<name>} row.

Score = 1 if both pass; else 0.

Gotchas

  • Idempotent: resuming an already-running agent is a no-op pass.
  • If the agent has already hit max_ticks, resuming alone will not

restart ticks - use /snappy-go <name> <prompt> <new_max_ticks> to bump the cap.

Rubric

criteria:
  - name: agent_status_updated
    kind: deterministic
    check: "The 'status' field in 'state/agents/<name>.json' is 'running' after skill execution."
  - name: log_entry_created
    kind: deterministic
    check: "A log entry with 'action:\"resume\"' and 'id:<name>' is present in 'state/log/agents.ndjson' after skill execution."
  - name: correct_tick_headroom_quoted
    kind: judge
    check: "The operator message correctly quotes the 'ticks/max_ticks' value for the agent as per 'state/agents/<name>.json'."

AGENTS.md- what the AI loads when this skill comes up

snappy-resume - loader

Per-turn rules for the snappy-resume skill. Full reference: state/skills/snappy-resume/SKILL.md. Do not skip these.

Critical Rules

  • Idempotent: resuming an already-running agent is a no-op pass.

Commands

| ui model | live composition via compose_inline, persisted as artifact lang_body, reopened with OpenArtifact | |invoke: see state/skills/snappy-resume/SKILL.md Steps section |eval log: state/log/evals.ndjson (skill: "snappy-resume")

Self-Test

An agent reading this should correctly:

  1. [ ] Know which lib/bin artifact backs this skill (or that it is prose-only)
  2. [ ] Know what to write to state/log/evals.ndjson after invoking
  3. [ ] Know the eval mode (auto / shape / manual) from the .md frontmatter

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 - 2 inline code blocks live in SKILL.md above (no state/bin/ sidecar yet).

how we check it- the checks, plus the last 10 runs

rubric auto-shape no rubric declared
recent no runs actor/auditor: unverifiable
deps none declared

no recent runs logged - the eval contract is declared but nothing has been graded yet