Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

pi-check-session-logs

Étoiles98

Forks12

Mis à jour10 avril 2026 à 09:44

Analyze pi-go session logs (last 24h by default) for tool call errors, deduplicate them, and present a summary table with error patterns and counts.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

dimetron

dimetron/pi-go

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

Explorateur de fichiers

2 fichiers

SKILL.md

readonly

name	pi-check-session-logs
description	Analyze pi-go session logs (last 24h by default) for tool call errors, deduplicate them, and present a summary table with error patterns and counts.

Check Session Logs

Scan recent pi-go session logs for tool call errors, deduplicate by pattern, and present results.

Steps

Run the analysis script (scans last 24h by default, override with HOURS=N):

bash .pi-go/skills/pi-check-session-logs/analyze.sh

To scan a different time window:

HOURS=48 bash .pi-go/skills/pi-check-session-logs/analyze.sh

Present the raw output to the user as-is — the script already formats a markdown table.
Suggest optimizations based on the error patterns:
- For "not found" errors: suggest better path resolution or fallback logic
- For "permission denied": suggest sandbox configuration changes
- For "exit code" failures: suggest build/test fixes
- For repeated tool errors: suggest system prompt improvements to avoid the pattern
- For STREAM_ERROR: suggest retry/reconnect improvements
Extract actionable fixes — After presenting the summary, create (or update) an actionable fixes document:
```
mkdir -p ./specs/issues/001-session-errors
echo "<research>" > ./specs/issues/001-session-errors/PROMPT.md
```
This file should contain a prompt that can be loaded to guide the agent toward fixing the detected error patterns. Structure it with sections for:
- The top N error patterns are detected (with specific examples)
- Corresponding fix suggestions per pattern
- Context about when each fix applies (which tools, which scenarios)
Use this format for the prompt file:
```
# Session Error Fix Prompts

## Pattern: [error name]
- **Detected in**: [sessions/files where found]
- **Fix suggestion**: [specific actionable steps]
```
If the file already exists, update it to include new patterns while preserving existing ones.

Examples

/pi-check-session-logs — Analyze logs from last 24h
/pi-check-session-logs HOURS=48 — Analyze logs from last 48h

Run the analysis for the findings

Research on each issue using subagent - for each issue with priority, score, if it's going to be implemented or rejected.

Save the findings in ./specs/issues/001-session-errors/PROMPT.md

Plus depuis ce dépôt

même dépôt

memory-index

dimetron/pi-go

Index a folder's contents into the MemPalace semantic memory for search and retrieval. Use this skill whenever the user asks to "index a folder", "index a directory", "index memory", "mine a project into memory", "make a folder searchable", "embed a folder", "ingest code into the palace", or "index this directory for semantic search". Covers the full flow: model download, mempalace.yaml room configuration, mining, and verification via search. Also trigger when the user says "memory index", "index memory of folder", or asks how to make a project's code semantically searchable with pi-go's MemPalace.

2026-07-1198

ponytail

dimetron/pi-go

Lazy senior dev mode — always pick the simplest solution that works. Use this skill whenever writing, refactoring, or reviewing code to keep changes minimal: prefer the standard library, native platform features, and already-installed dependencies over new code or dependencies. Trigger when the user says "ponytail", "keep it simple", "simplest thing that works", "don't over-engineer", "lazy mode", or asks to avoid unnecessary abstractions, boilerplate, or premature complexity. The best code is the code never written.

2026-06-2298

check-linters-before-commit

dimetron/pi-go

Before any commit, run linters, vet, tests, and build verification; do not commit until checks pass

2026-04-1098

code-guidelines-go

dimetron/pi-go

Go 1.24–1.26 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2 configuration, slog logging, and manual dependency injection with functional options. Always consult this skill before generating Go code for pi-go, even for small snippets, to ensure every output is idiomatic and modern.

2026-04-1098

code-review-pi

dimetron/pi-go

Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to ./specs/issues/003-code-review-pi/PROMPT.md. Use before committing changes.

2026-04-1098

design-review

dimetron/pi-go

Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.

2026-04-1098

Check Session Logs

Scan recent pi-go session logs for tool call errors, deduplicate by pattern, and present results.

Steps

Run the analysis script (scans last 24h by default, override with HOURS=N):

bash .pi-go/skills/pi-check-session-logs/analyze.sh

To scan a different time window:

HOURS=48 bash .pi-go/skills/pi-check-session-logs/analyze.sh

Present the raw output to the user as-is — the script already formats a markdown table.

Suggest optimizations based on the error patterns:

For "not found" errors: suggest better path resolution or fallback logic
For "permission denied": suggest sandbox configuration changes
For "exit code" failures: suggest build/test fixes
For repeated tool errors: suggest system prompt improvements to avoid the pattern
For STREAM_ERROR: suggest retry/reconnect improvements

Extract actionable fixes — After presenting the summary, create (or update) an actionable fixes document:

mkdir -p ./specs/issues/001-session-errors
echo "<research>" > ./specs/issues/001-session-errors/PROMPT.md

This file should contain a prompt that can be loaded to guide the agent toward fixing the detected error patterns. Structure it with sections for:

The top N error patterns are detected (with specific examples)
Corresponding fix suggestions per pattern
Context about when each fix applies (which tools, which scenarios)

Use this format for the prompt file:

# Session Error Fix Prompts

## Pattern: [error name]
- **Detected in**: [sessions/files where found]
- **Fix suggestion**: [specific actionable steps]

If the file already exists, update it to include new patterns while preserving existing ones.

Examples

/pi-check-session-logs — Analyze logs from last 24h

/pi-check-session-logs HOURS=48 — Analyze logs from last 48h

Run the analysis for the findings

Research on each issue using subagent - for each issue with priority, score, if it's going to be implemented or rejected.

Save the findings in ./specs/issues/001-session-errors/PROMPT.md