sigmacodeat/sigmabrain/candidate-match

Claude Code and agent skill by sigmacodeat/sigmabrain

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Matches candidates to an open role from the firm's talent graph: ranks candidates by fit (experience, sector, seniority, availability, prior contact), explains each match, and flags conflicts (off-limits, placed recently, client overlap). Surfaces who-knows-whom for warm intros. Shortlist support for the consultant; the human decides who to approach.

Install

npx vskill@latest install sigmacodeat/sigmabrain/candidate-match

SKILL.md

The same SKILL.md was published earlier as sigmacodeat/sigmabrain/candidate-match.

Candidate-Match Skill

Warning: AI-assisted shortlist from the talent graph. The consultant
decides who to approach; respect off-limits and data-protection rules.

Contract

This skill guarantees:

  1. Candidates are ranked by explicit fit criteria (experience, sector, seniority, availability).
  2. Each match has a one-line rationale and the source.
  3. Conflicts are flagged (off-limits, recently placed, client overlap).
  4. Output is shortlist support, marked human-decides.

Trigger Conditions

Use to build a shortlist for a role. Do NOT use to write one candidate's profile (→ candidate-dossier) or review the pipeline (→ pipeline-review).

Protocol

  1. Parse the role: must-haves, sector, seniority, location, constraints.
  2. Search the talent graph; rank by fit.
  3. Explain each match; surface warm-intro paths (who-knows-whom).
  4. Flag conflicts/off-limits.

Output Format

## Shortlist — [Role] @ [Client]
### Ranked candidates
1. [Candidate] — fit: [rationale] — warm intro via [person] (source)
### Conflicts / off-limits
---
⚠️ AI-assisted; consultant decides. candidate-match v1.0.0

Anti-Patterns

  • ❌ Proposing an off-limits or recently-placed candidate without flagging it.
  • ❌ A ranking with no fit rationale.
  • ❌ Ignoring data-protection / consent constraints on candidate data.

Error Handling

  • Role under-specified → list the must-haves needed before ranking.
  • Thin talent graph → state coverage; recommend importing past searches.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sigmacodeat/sigmabrain/candidate-match/badge)](https://verified-skill.com/skills/sigmacodeat/sigmabrain/candidate-match)

Something wrong with this skill or its page? Tell us.