Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Context Task Classifier

ASecurity

Usar antes de compactar contexto para clasificar la tarea del turno actual.

50 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsgobash

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/27/2026

$npx -y skills add gonzalezpazmonica/savia --skill context-task-classifier --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Context Task Classifier?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Context Task Classifier
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/gonzalezpazmonica-context-task-classifier/badge)](https://www.skillsdirectory.com/skills/gonzalezpazmonica-context-task-classifier)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
layer: peripheral
name: context-task-classifier
description: Usar antes de compactar contexto para clasificar la tarea del turno actual.
metadata:
  # --- metadata.savia.* (SE-333) ---
  savia.input: text
  savia.maturity: stable
  savia.output: json
---

# context-task-classifier

Clasificador determinístico de turnos para rate-distortion-aware compression
(SE-029). Cada clase tiene un ratio máximo de compresión y una marca
`frozen` que indica si el contenido queda exento de compactación.

## Input

Un turno de conversación (texto, markdown, diff, o stack trace) pasado
por `--stdin` o `--input FILE`.

## Output

Una sola línea con la clase (modo texto) o JSON con detalles (modo `--json`):

```json
{
  "class": "decision",
  "max_ratio": 5,
  "frozen": "true",
  "words": 4,
  "lines": 1,
  "scores": {
    "decision": 3,
    "spec": 0,
    "code": 0,
    "review": 0,
    "context": 0,
    "chitchat": 0
  }
}
```

## 6 clases de tarea

| Clase | max_ratio | frozen | Señales principales |
|---|---|---|---|
| `decision` | 5:1 | true | APPROVED/merge/commit, yes/no verdicts |
| `spec` | 3:1 | true | SPEC-NNN, SE-NNN, PBI-NNN, AC-MM, frontmatter |
| `code` | 10:1 | partial | fences ```, diff markers, Traceback/Error |
| `review` | 15:1 | false | PASS/FAIL/WARN, G\d+ gates, judge findings |
| `context` | 25:1 | false | markdown largo, headings, bullets, >100 words |
| `chitchat` | 80:1 | false | ≤8 words, thanks/ok/gracias/hi |

## Ejemplos de uso

```bash
# Clasifica un mensaje de chat
echo "APPROVED — merge PR #624" | scripts/context-task-classify.sh --stdin
# → decision

# Clasifica un diff file en JSON
scripts/context-task-classify.sh --input /tmp/pr.diff --json

# Integración con context-budget (SE-029 Slice 4, futuro):
#   foreach turn in session:
#     class = classify(turn)
#     apply max_ratio[class] when compacting
#     skip if frozen[class]
```

## Reglas de clasificación

1. **Scoring aditivo** — cada patrón matched suma puntos a su clase.
2. **Tie-breaking por prioridad** — empates se resuelven a favor de la
   clase más estricta (decision > spec > code > review > context >
   chitchat). Err del lado de preservar contenido.
3. **Fallback** — sin señal: ≤15 words → chitchat, else context.

## Integración con SE-029

Este clasificador es el input del **operational point selector**
(SE-029-O, Slice 4) que elige R(D) óptimo por turn:

```
Turn → classify() → max_ratio_class
                 → frozen? → compress-skip-frozen.sh hook
                 → else: compress(ratio = min(budget_target, max_ratio_class))
```

## Ref

- `scripts/context-task-classify.sh` — implementación
- `tests/test-context-task-classify.bats` — 34 tests (auditor score 98)
- `docs/propuestas/SE-029-rate-distortion-context.md` §2
- `scripts/context-distortion-measure.sh` — SE-029 Slice 1 (distortion metric)

Attribution

gonzalezpazmonicagonzalezpazmonica
View sourceSee grades on GitHubMore from gonzalezpazmonica →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →