Observe

Sustained neutral pattern recognition across systems without urgency or intervention. Maps naturalist field study methodology to AI reasoning: framing the observation target, witnessing with sustained attention, recording patterns, categorizing findings, generating hypotheses, and archiving a pattern library for future reference. Use when a system's behavior is unclear and action would be premature, when debugging an unknown root cause, when a codebase change needs its effects witnessed before further changes, or when auditing own reasoning patterns for biases or recurring errors.

45 stars 4 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add pjt222/agent-almanac --skill observe
Manual install
git clone --depth 1 https://github.com/pjt222/agent-almanac.git /tmp/agent-almanac
mkdir -p ~/.claude/skills
cp -r /tmp/agent-almanac/i18n/caveman-lite/skills/observe ~/.claude/skills/observe

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Observe

Conduct a structured observation session — frame the target, witness with sustained neutral attention, record patterns without interpretation, categorize findings, generate hypotheses from patterns, and archive observations for future reference.

## When to Use

- A system's behavior is unclear and action without observation would be premature
- Debugging a problem where the cause is unknown — observation before intervention prevents masking symptoms
- A codebase or system has been changed and the effects need to be witnessed before further changes are made
- Understanding user behavior patterns over a conversation to improve future interactions
- Auditing own reasoning patterns for biases, habits, or recurring errors
- After `learn` has built a model that needs validation through observation of the system in action

## Inputs

- **Required**: Observation target — a system, codebase, behavior pattern, user interaction, or reasoning process to observe
- **Optional**: Observation duration/scope — how long or deep to observe before concluding
- **Optional**: Specific question or hypothesis to guide observation focus
- **Optional**: Prior observations to compare against (detecting change over time)

## Procedure

### Step 1: Frame — Set the Observation Focus

Define what is being observed, why, and from what perspective.
Read the full skill on GitHub

Details

Skill name
observe
Path
i18n/caveman-lite/skills/observe/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Observe skill do?

Sustained neutral pattern recognition across systems without urgency or intervention. Maps naturalist field study methodology to AI reasoning: framing the observation target, witnessing with sustained attention, recording patterns, categorizing findings, generating hypotheses, and archiving a pattern library for future reference. Use when a system's behavior is unclear and action would be premature, when debugging an unknown root cause, when a codebase change needs its effects witnessed before further changes, or when auditing own reasoning patterns for biases or recurring errors.

How do I install the Observe skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add pjt222/agent-almanac --skill observe. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Observe popular?

It lives in pjt222/agent-almanac, which has 45 GitHub stars and 4 forks, and is included in 1 curated skill list.

Related skills

Adapt Architecture

45

pjt222/agent-almanac

Execute structural metamorphosis using strangler fig migration, chrysalis phases, and interface preservation. Covers transformation planning, parallel running, progressive cutover, rollback design, and post-metamorphosis stabilization for system architecture evolution. Use when assess-form has classified the system as READY for transformation, when migrating from monolith to microservices, when replacing a core subsystem while dependents continue operating, or when any architectural change must be gradual rather than big-bang.

Software DevelopmentIn 1 list

Adaptic

45

pjt222/agent-almanac

Master skill composing the 5-step synoptic cycle for panoramic synthesis across multiple domains. Orchestrates meditate, expand-awareness, observe, awareness, integrate-gestalt, and express-insight into a coherent process that produces unified understanding rather than sequential compromise. Use when a problem genuinely spans 3+ domains and the interactions between domains matter more than depth in any one, when sequential analysis feels like compromise rather than integration, or before major architectural decisions affecting multiple stakeholders.

OtherIn 1 list

Add Puzzle Type

45

pjt222/agent-almanac

Scaffold a new puzzle type across all 10+ pipeline integration points in jigsawR. Creates the core puzzle module, wires it into the unified pipeline (generation, positioning, rendering, adjacency), adds ggpuzzle geom/stat layers, updates DESCRIPTION and config.yml, extends the Shiny app, and creates a comprehensive test suite. Use when adding a completely new puzzle type to the package or following the 10-point integration checklist to ensure nothing is missed end-to-end.

Testing & QAIn 1 list

Policy Redraft

43

AlsKozlov/ru-legal

Auto-draft изменений в нашем ЛНПА с учётом нового regulatory requirement. HITL approval перед finalize. Output: redline diff version + clean новая редакция. Cross-ref `corporate-law/policy-drafting` framework.

Software Development

Monitor Binary Version Baselines

45

pjt222/agent-almanac

Establish and maintain longitudinal baselines of CLI binary contents across versions. Covers marker selection by category (API / identity / config / telemetry / flag / function), weighted scoring, threshold-based system-presence detection, and per-version baseline records. Use when tracking a feature's lifecycle across releases, when probing for dark-launched or removed capabilities, or when verifying that a scanning tool still catches known-good markers on old binaries.

Software DevelopmentIn 1 list

Probe Feature Flag State

45

pjt222/agent-almanac

Probe the runtime state of a named feature flag in a CLI binary. Covers the four-pronged evidence protocol (binary strings, live invocation, on-disk state, platform cache), the four-state classification (LIVE / DARK / INDETERMINATE / UNKNOWN), gate-vs-event disambiguation, conjunction-gate handling, and skill-substitution scenarios where a flag appears DARK but the capability is delivered by other means. Use when verifying whether a documented or inferred capability has rolled out, when auditing dark-launched features, or when a prior probe's conclusions need refreshing against a new binary ve

Software DevelopmentIn 1 list

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.