intelligence-investigator

Generate intelligence briefings for the planning dashboard. Use this skill whenever a request file appears in `.planning/console/inbox/pending/` whose `type` field starts with `intelligence.` (refresh_briefing, triage_finding, snapshot_diff, investigate_section, dismiss_finding). The skill reads the per-project KB at `.gsd/intelligence/intelligence.db`, synthesizes a briefing with a causal hypothesis + acknowledged uncertainty + confidence label and ranked moves, then writes the result back to the KB. Always trigger this skill for these request types — do not generate briefings manually.

Ir para a instalação

Repositório: Tibsfox/gsd-skill-creator
Última atividade na origem: 6 de junho de 2026 às 02:15
Idioma detectado do SKILL.md: inglês
Estrelas: 69
Forks: 9

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/Tibsfox/gsd-skill-creator --skill intelligence-investigator

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

Explorador de arquivos

8 arquivos

SKILL.md

Instruções da origem · Visualização somente leitura

Voltar à pesquisa Voltar à instalação

goal-ambiguity-gate

Use the moment a request is underspecified and you are about to act on an ASSUMED goal. Enumerate the candidate goals the request could mean, project the action or artifact each one implies, and check whether they diverge: if two or more plausible goals lead to materially different actions or artifacts, ask exactly ONE targeted clarifying question; otherwise proceed on the most-likely goal and state the assumption in one line. Clarification is an evidence-producing action, not a delay — but one question, never an interrogation. Distinct from gsd-spec-phase (GSD-phase-bound, emits a heavy SPEC.md) and intent-router (fetch strategy, not goal disambiguation). Backed by agent goal-state inference (arxiv 2606.16813v1). Triggers on acting under an assumed goal when the request admits more than one materially different reading.

2026-07-19

memory-hubness-gate

Use at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

2026-07-19

memory-use-warrant

Run this appropriateness check the moment you are about to integrate a retrieved long-term memory — a Grove content-addressed hit, a chroma/pgvector neighbour, a memory-consolidation digest, or a MEMORY.md line — into a response, especially anything touching private origins, Fox Companies IP, credentials, or Center Camp / consent-governed content. It answers a question intent-router never asks: not WHAT to fetch or HOW, but WHETHER a correctly-retrieved item should reach output. Relevance is not appropriateness — a perfect similarity match can still be a boundary violation. Default is FAIL-CLOSED: if in-context authorization is uncertain, the memory may inform behaviour but must not be surfaced. Backed by RBI-Eval (arxiv 2606.06055v1). Triggers on surfacing recalled sensitive memory into a response.

2026-07-19

Ver todas deste repositório

name	intelligence-investigator
description	Generate intelligence briefings for the planning dashboard. Use this skill whenever a request file appears in `.planning/console/inbox/pending/` whose `type` field starts with `intelligence.` (refresh_briefing, triage_finding, snapshot_diff, investigate_section, dismiss_finding). The skill reads the per-project KB at `.gsd/intelligence/intelligence.db`, synthesizes a briefing with a causal hypothesis + acknowledged uncertainty + confidence label and ranked moves, then writes the result back to the KB. Always trigger this skill for these request types — do not generate briefings manually.
version	1.0.0
format	"2025-10-02T00:00:00.000Z"
triggers	["console-inbox request type starts with intelligence.* (refresh_briefing, triage_finding, snapshot_diff, investigate_section, dismiss_finding)"]
updated	"2026-05-02T00:00:00.000Z"
status	ACTIVE
allowed-tools	Read, Glob, Bash(sqlite3:), Bash(git:), Bash(node:), Bash(bun:), Write

Intelligence Investigator

You are responsible for generating planning briefings for the GSD intelligence dashboard. The dashboard surfaces these briefings to the developer at the start of every planning meeting. You run inside a gsd-skill-creator session that is already watching .planning/console/inbox/pending/.

When to activate

Activate when you find a file matching req_*.json in .planning/console/inbox/pending/ whose type field starts with intelligence.:

intelligence.refresh_briefing — full project briefing refresh
intelligence.triage_finding — single finding deep-dive
intelligence.snapshot_diff — explain what changed between two snapshots
intelligence.investigate_section — investigate a specific section of code
intelligence.dismiss_finding — record a dismissal with rationale

Process

1. Parse the request

Read the request file. Extract id, type, project, branch, payload, respond_to, timeout_hint_ms. The request fields define the scope:

payload.since_snapshot — for diff-based requests
payload.scope — list of section/file globs to focus on
payload.conversation_text — recent dashboard discussion (already redacted)
payload.finding_id — for triage requests

2. Load KB context

Run bash scripts/load-kb-context.sh <project> to extract a redacted JSON context summary. The script:

Reads top 30 findings by severity × confidence from the per-project DB
Reads in-flight bundles + decisions
Reads recent meeting record paths (last 3)
Reads recent snapshot diffs (last 3)
Redacts secrets (API keys, tokens, password fragments, SSH keys) before emitting context (S14, D-25-31)
NEVER emits raw source-file content (D-25-30)

The output is structured JSON; parse it before reasoning.

3. Synthesize briefing

Following references/briefing-format.md, write a briefing of 2-3 paragraphs that:

intelligence-investigator

Opções de instalação

Revise os arquivos de origem

Intelligence Investigator

When to activate

Process

1. Parse the request

2. Load KB context

3. Synthesize briefing

Intelligence Investigator

When to activate

Process

1. Parse the request

2. Load KB context

3. Synthesize briefing

4. Rank suggested moves

5. Self-check the briefing

6. Write briefing to KB

7. Write status to outbox

Failure paths

Critical constraints

Reference files

intelligence-investigator

Informações da origem

Opções de instalação

Revise os arquivos de origem

Mais deste repositório

Intelligence Investigator

When to activate

Process

1. Parse the request

2. Load KB context

3. Synthesize briefing

Mais deste repositório

Intelligence Investigator

When to activate

Process

1. Parse the request

2. Load KB context

3. Synthesize briefing

4. Rank suggested moves

5. Self-check the briefing

6. Write briefing to KB

7. Write status to outbox

Failure paths

Critical constraints

Reference files