skills/magnus919_agent-skills
1
0
Fork 0
mirror of https://github.com/magnus919/agent-skills.git synced 2026-09-11 19:47:12 +03:00
Code Issues Packages Projects Releases Wiki Activity
824 Commits 11 Branches 10 Tags
main
Commit Graph
5 Commits
Author SHA1 Message Date
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> d1e282a95d docs(transistor): scope publish audio-guard and add missing trigger rows 
Document that the publish audio-guard fires only for --status published
(scheduling intentionally precedes audio attach) and that its pre-publish
episode GET consumes one rate-limit slot, relevant to bulk re-publish
loops.

Add references/skill-triggers.md rows for transistor and trakt, the two
thickened skills missing from the trigger index; phrasing follows each
skill frontmatter description.

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
 2026-08-30 01:52:43 -04:00
Magnus Hedemarkandfactory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> 05b99be6ec docs(transistor): thicken podcast hosting skill against current API research 
Full skill-builder rebuild of transistor per issue #407:

- scripts/transistor (renamed from transistor-cli): 19 commands covering the
  verified API surface - user probe (GET /v1; the /v1/user route does not
  exist), shows/episodes with corrected pagination[page]/pagination[per],
  the dedicated episode publish endpoint (PATCH /v1/episodes/:id/publish
  with episode[status]=draft|scheduled|published), authorize-upload flow,
  the three real analytics routes with downloads[] array summing,
  subscriber management incl. batch, and webhooks. Write bodies are
  form-encoded bracket keys exactly as documented; dry-run plans carry
  method/path/params/body; publish guard refuses audio-less episodes.
  Fixed stale claims: /analytics/show -> /v1/analytics/..., totals ->
  downloads arrays, pagination[limit] -> pagination[per], user email ->
  name/time_zone, dropped invented episodes_count/subscribers_count and
  POST /v1/shows (show creation is dashboard-only).
- scripts/test_transistor.py: 50 offline tests (pytest + unittest green,
  proxy-trap clean) covering help, argument errors, dry-run plans, canned
  JSON:API compound-document parsing (data/attributes/relationships/
  included[]), write-path body shapes, publish guard, create->audio->
  publish pipeline, and HTTP error signatures.
- references/: auth+JSON:API envelope with jq patterns, endpoint catalog,
  publish lifecycle with documented request/response shapes, gotchas
  field guide + worked recipes; all cited to live-verified sources.
- evals/evals.json: 8 schema-v1 cases incl. two should-not-trigger probes.
- SKILL.md rewritten (308 lines), README refreshed, root README blurb and
  generated catalogs synced (marketplace.json + llms.txt descriptions).

Publish-body shape reconciliation: the contract's data.id+data.type JSON:API
PATCH premise was falsified by current official docs (verified 2026-08-29)
and the flimzy/transistor Go SDK; implemented reality escalated in handoff
(see library/transistor-api-facts.md).

Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
 2026-08-29 22:02:23 -04:00
Magnus Hedemark a5f7e74972 fix: resolve skill audit findings 2026-07-11 09:24:58 -04:00
Magnus Hedemark 738ec715e7 Add human-focused README.md to every skill and bundle directory 
Each README is written for a human audience, explaining:
- What the skill does (not what format it follows)
- What benefit the user gets from installing it
- Quick setup and usage patterns
- When to load/trigger the skill
- What scripts, references, and templates it ships

data-scientist already had a README — left unchanged.

48 READMEs added across all skill and bundle directories.
 2026-07-09 22:30:12 -04:00
Magnus Hedemark f5521d97da feat: add transistor skill — TRANSISTOR CLI 2026-05-21 23:46:31 -04:00