skilld
All skills
simota avatar

/sage

@16a3f28
by shingo imotasimota/agent-skills85 stars
15

Advising founders YC-style — socratic probing to surface the #1 bottleneck, anti-pattern detection, and 1-2 week action items. Not for brainstorming (Riff) or long-term scenarios (Helm).

Ask your Agent

Use this Skill: https://skilld.dev/gh/simota/agent-skills/sage

This session only. Nothing lands on disk.

referenceautorun-schema.md

≈222 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Sage — AUTORUN _STEP_COMPLETE Schema

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling).

Sage-specific _STEP_COMPLETE.Output schema:

_STEP_COMPLETE:
  Agent: Sage
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    Task_Type: 1on1 | group | triage | retro | pitch
    Bottleneck: <one-sentence statement of the #1 problem>
    Patterns_Cited:
      - id: <P-XX | AP-XX>
        summary: <one-line summary>
    Anti_Patterns_Detected:
      - id: <AP-XX>
        summary: <one-line summary>
        signals: [<signal_1>, <signal_2>]
    Actions:
      - owner: <user/team>
        task: <observable outcome>
        due: <YYYY-MM-DD>
    Next_Checkpoint: <YYYY-MM-DD>
    Handoff_Target: <Builder | Echo[demand] | Sherpa | none>
  Next: <Builder | Echo[demand] | Sherpa | DONE>
  Reason: <why this outcome>

Source: SKILL.md on GitHub

Third-party checks

No alerts5mo3 checks · Risk SAFE
  • Gen Agent Trust Hub5mo

    The 'Sage' skill is a structured advisory framework designed to provide startup mentoring and bottleneck identification. It operates through a series of Socratic probing steps and pattern-matching logic documented in Markdown files. The security analysis found no malicious code, data exfiltration patterns, obfuscation, or unauthorized command execution. The skill is entirely instruction-based and does not include executable scripts or external dependencies.

  • Socket5mo

    No alerts

  • Snyk5mo

    Risk: LOW · No issues

Provenance

Signed by skilld at 16a3f28. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated last month

README badge

README badge for simota/agent-skills/sage