post

Unified distribution router for all snappy-* skills.

Ported from kernel snappy-post in Phase 0.5. See state/lib/post.ts for the full API surface.

Steps

• createPost() - see state/lib/post.ts
• sendMessage() - see state/lib/post.ts
• sendText() - see state/lib/post.ts

Eval

Actor: the exported functions in state/lib/post.ts. Auditor: none wired yet - eval is manual (Robert review). File a state/log/pending-eval.ndjson row on each run.

Score convention:

Gotchas

via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)

1. realpathSync(process.argv[1]) CLI guard wrapped in try/catch

• See the kernel SKILL.md for the original long-form guidance if you need it

(read-only reference at the kernel path above).

Graduation

This skill is prose. Graduate by defining a deterministic auditor and flipping eval: auto.

Rubric

criteria:
  - name: posts_all_channels_called
    kind: judge
    check: "The skill calls at least one function from each of the 'linkedin' and 'slack' dependencies for relevant inputs."
  - name: logging_entry_present
    kind: deterministic
    check: "A new row is appended to 'state/log/pending-eval.ndjson' for each skill execution."
  - name: api_surface_used_correctly
    kind: judge
    check: "The skill uses the functions createPost(), sendMessage(), and sendText() as defined in 'state/lib/post.ts' with appropriate arguments based on the input."

post - loader

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

Critical Rules

• NEVER call the lib's createPost or sendMessage directly - kernel had a name collision; the patched names are createLinkedInPost and sendSlackMessage in state/lib/post.ts.
• ALWAYS run final draft text through state/lib/voice.ts checkTone() BEFORE calling any post fn - channel APIs do not gate, and a hype-word draft will ship.
• ALWAYS verify the post landed via independent fetch from a different session (actor != auditor). The write API's 200 response is not evidence.
• NEVER fan out parallel browser writes against one session - DOM-mutation agents silently drop writes. Serialize uploads.

Commands

| ui dashboard | state/skills/post/resources/ui.openui | |invoke (TS): import { createLinkedInPost, sendSlackMessage, sendText } from "../lib/post.ts" |verify (LinkedIn): independent fetch via state/lib/linkedin.ts |verify (Slack): independent fetch via state/lib/slack.ts |eval log: state/log/pending-eval.ndjson (skill: "post") - manual until auditor wired

OpenUI Resource

• Skill-owned OpenUI Lang resource: state/skills/post/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.

Known Pitfalls

• The Phase 0.5 port renamed two functions to avoid kernel collision; if you copy/paste from kernel docs the call name will be wrong.
• This is a router, not a channel. It dispatches to lib/linkedin.ts, lib/slack.ts, lib/telegram.ts, lib/whatsapp.ts under the hood.

Self-Test

An agent reading this should correctly:

1. [ ] Use createLinkedInPost (not createPost) when posting to LinkedIn
2. [ ] Run checkTone() on the draft before calling any post fn
3. [ ] Verify a post via independent fetch, not the write response

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] post: <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)] post: <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.