snappy-default

One job: clear state/log/byline-view.json so the byline returns to its default 1-2 line summary. Counterpart to /snappy-agents and any future channel-flip skills.

Usage

/snappy-default

Steps

1. Run:

   python3 -c "import json; open('$HOME/projects/snappy-os/state/log/byline-view.json','w').write(json.dumps({'view':'default','set_at':''})+'\n')"

1. Confirm by running bash $HOME/projects/snappy-os/state/bin/statusline.sh

- should show the compact summary, not a per-agent list.

1. Log eval row to state/log/evals.ndjson:

{ts, skill:"snappy-default", verb:"clear-view", score: 1 if cleared else 0}

Why

The 5-min auto-revert in statusline.sh handles the common case (operator forgets they flipped the view). This skill is the manual escape hatch.

Eval

Shape-gate:

• state/log/byline-view.json has view: "default" after invocation.
• Statusline render does NOT contain the agents-detail header line.

Score = 1 if both pass; else 0.

Gotchas

• Idempotent: clearing an already-default view is a no-op pass.
• Same as /snappy-agents: no cron, no daemon - statusline reads on render.

Rubric

criteria:
  - name: byline_view_is_default
    kind: deterministic
    check: "The content of $HOME/projects/snappy-os/state/log/byline-view.json should be {\"view\":\"default\",\"set_at\":\"\"} after skill execution."
  - name: statusline_shows_compact_summary
    kind: deterministic
    check: "The output of 'bash $HOME/projects/snappy-os/state/bin/statusline.sh' should not contain an agents-detail header line after skill execution."
  - name: eval_row_logged
    kind: deterministic
    check: "A new row `{ts, skill:\"snappy-default\", verb:\"clear-view\", score: 1}` should be appended to $HOME/projects/snappy-os/state/log/evals.ndjson, where ts is the current timestamp."

snappy-default - loader

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

Critical Rules

• Idempotent: clearing an already-default view is a no-op pass.

Commands

| ui dashboard | state/skills/snappy-default/resources/ui.openui | |invoke: see state/skills/snappy-default/SKILL.md Steps section |eval log: state/log/evals.ndjson (skill: "snappy-default")

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

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] snappy-default: <what was missing>" >> state/log/loader-feedback.log

<!-- kernel-ok: historical attribution for the PID-loader pattern. -->

Self-correcting loader (PID feedback)

This is the rule that makes loaders learn. Ported from snappy-kernel, where it demonstrably worked: the snappy-dom-cartographer skill mapped Skool admin UI once, every later ship-agent inherited the full map for free.

Before you finish, do two things:

1. Fix gaps (P - proportional). MANDATORY. If this loader didn't cover your case - if you had to read another file, run an undocumented command, work around a wrong selector, or discover a quirk - you MUST attempt an Edit to this AGENTS.md before you log.

• Default action: edit this file. Surgical. Add the missing line, table

row, or code example where it belongs. No restructuring.

• Only LOGGED is allowed when: the fix needs >10 lines, spans multiple

files, or requires a structural rewrite. In that case the state/regen/drain.sh queue picks it up asynchronously.

• "I didn't have time" / "it's minor" / "the next agent will figure it out"

are NOT valid reasons. Minor gaps compound - that's the whole point of this loop.

• Concrete example of a valid P-fix: discover agent-browser screenshot

takes path positionally not as --output <path>. One line in a table. Edit it in. Do not just log it.

• The goal: the next agent never has to leave the loader.

2. Log the result.

echo "[$(date -u +%FT%TZ)] snappy-default: <what was missing or fixed> [FIXED|LOGGED]" >> state/log/loader-feedback.log

• FIXED = you patched this loader inline (P-fix).
• LOGGED = too large for inline; the PostToolUse enqueue + Stop-hook drain

will rewrite the loader from scratch on next session-end.

Do not skip this. Every agent run must leave the system better than it found it. The loader is the setpoint; you are the sensor; the gap is the error signal; closing the gap is the correction.

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/snappy-default/resources/ui.openui. Read it before rendering or editing this skill's generated component surface.
• Treat this resource as a first-class artifact of the skill, not a generic chat response. Improve it when the skill's user-facing output needs to become richer.
• System resources compose OpenUI primitives and inherit SnappyChat tokens. Use ui_contract: branded in SKILL.md only for deliberate platform or client visuals.