CD publicar-ig
Skill para publicar fotos, carruseles (1-10 slides) o reels en el Instagram profesional de la usuaria desde su agente, con la conexión de Instagram que ELLA conectó (Composio, o Zapier si lo tiene). Activar SIEMPRE que pida: "publica esto en Instagram", "/publicar-ig", "sube este carrusel a IG", "publica este reel", "manda esto a Instagram", "haz el post en IG", "publica lo que acabamos de hacer", o cualquier variación que combine un archivo/carpeta de imagen o video con la intención de publicarlo en Instagram. Usa URLs públicas (las de Higgsfield, una que ella dé, o su propio repo público de GitHub si lo conectó). Nunca publica sin mostrar el preview completo y recibir ✅ explícito por Telegram. NO maneja Stories.
Skill para publicar fotos, carruseles (1-10 slides) o reels en el Instagram profesional de la usuaria desde su agente, con la conexión de Instagram que ELLA…
As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 41/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 85Steps. 41 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2499 tokens
- low The response is described with custom markup (9 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 723: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.