agentleFS
synaptiaisynaptiai/agent-capability-standard/skills/observe/SKILL.md

observe

Skill6 starsChanged 14 days agoApache-2.0View on GitHub

Watch and report current state of a target system, process, or entity. Use when monitoring status, inspecting live systems, checking current conditions, or observing runtime behavior.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use design and ship.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Microsoft AzureSkill

    design

    Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If aspects not specified, observe: status, configuration, recent changes, anomalies

    line 42
  2. Distinctive:

    Use Read for file-based targets

    line 46
  3. Distinctive:

    Use Bash for process/system state (ps, systemctl status, etc.)

    line 47
  4. Distinctive:

    Verification tools: Read (to verify file observations)

    line 174
  5. Distinctive:

    NEVER modify the target during observation

    line 184
  6. Distinctive:

    Do not access targets outside authorized scope

    line 185
  7. Very specific:

    Never use observe for modification (use mutate)

    line 201
  8. Very specific:

    Avoid observe for pattern matching (use detect)

    line 202

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Intent

Observe and report the current state of a specified target without modifying it. This is the foundation for situational awareness and state modeling.

Success criteria:

  • Current state accurately captured with timestamp
  • Relevant aspects of the target documented
  • At least one evidence anchor per observation
  • Uncertainty explicitly noted where state is ambiguous

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

ParameterRequiredTypeDescription
targetYesstringWhat to observe (file path, URL, process, system)
aspectsNoarraySpecific aspects to focus on (e.g., ["status", "errors", "metrics"])

Inputs not listed here are outside the capability's contract: a workflow step that binds them gets W604 (STANDARD v1.1 §5.5).

Procedure

  1. Identify observation target: Clarify exactly what system, process, or entity to observe
    • Validate target is accessible and observable
    • Determine appropriate observation method (read file, query API, check process)
  2. Select observation aspects: Determine what properties/attributes to capture
    • If aspects not specified, observe: status, configuration, recent changes, anomalies
    • Prioritize aspects relevant to apparent context or goal
  3. Capture current state: Execute observation without modifying target
    • Use Read for file-based targets
    • Use Bash for process/system state (ps, systemctl status, etc.)
    • Record timestamp of observation
  4. Document observations: Structure findings with evidence
    • Note what was observed and when
    • Highlight notable conditions or anomalies
    • Record uncertainty where state is unclear
  5. Ground claims: Attach evidence anchors to all observations
    • Format: file:line for file content
    • Format: command:output for system observations

Output Contract

Return a structured object:

observation:
  target: string  # What was observed
  status: string  # Overall status assessment
  aspects:
    - aspect: string  # Name of observed aspect
      value: any  # Observed value or state
      notable: boolean  # Whether this is noteworthy
  anomalies: array[string]  # Unexpected findings
timestamp: string  # ISO 8601 timestamp
confidence: 0..1  # Based on observation quality
evidence_anchors: ["file:line", "command:output"]
assumptions: []  # What was assumed about the target
next_actions: array[string]  # 0-3 suggested follow-ups

Field Definitions

FieldTypeDescription
observation.targetstringIdentifier of what was observed
timestampstringISO 8601 date-time the observation was made
observation.statusstringSummary status (healthy, degraded, error, unknown)
observation.aspectsarrayList of observed aspects with values
confidencenumber0.0-1.0 based on observation completeness
evidence_anchorsarray[string]References to raw observation data

Examples

Example 1: Observe Process Status

Input:

target: "web-server process"
aspects: ["running", "memory", "connections"]

Output:

observation:
  target: "nginx process (PID 1234)"
  status: "healthy"
  aspects:
    - aspect: "running"
      value: true
      notable: false
    - aspect: "memory"
      value: "125MB RSS"
      notable: false
    - aspect: "connections"
      value: 847
      notable: true
  anomalies:
    - "Connection count higher than typical (avg: 200)"
timestamp: "2024-01-15T10:30:00Z"
confidence: 0.95
evidence_anchors:
  - "command:ps aux | grep nginx"
  - "command:netstat -an | grep :80"
assumptions:
  - "Process identified by name 'nginx'"
next_actions:
  - "Monitor connection trend over time"
  - "Check for connection leak if count continues rising"

Example 2: Observe File State

Input:

target: "config/database.yml"
aspects: ["content", "permissions", "modified"]

Output:

observation:
  target: "config/database.yml"
  status: "present"
  aspects:
    - aspect: "content"
      value: "PostgreSQL configuration with production credentials"
      notable: true
    - aspect: "permissions"
      value: "644"
      notable: true
    - aspect: "modified"
      value: "2024-01-14T15:22:00Z"
      notable: false
  anomalies:
    - "File permissions allow group/other read (sensitive credentials)"
timestamp: "2024-01-15T10:35:00Z"
confidence: 0.9
evidence_anchors:
  - "config/database.yml:1-25"
  - "command:ls -la config/database.yml"
assumptions:
  - "File contains database credentials based on content inspection"
next_actions:
  - "Review file permissions for security"
  - "Consider using environment variables for credentials"

Verification

  • Observation timestamp is current (within observation window)
  • At least one aspect was observed and documented
  • Evidence anchors exist for each notable observation
  • Target was not modified during observation
  • Anomalies are supported by evidence

Verification tools: Read (to verify file observations)

Safety Constraints

  • mutation: false
  • requires_checkpoint: false
  • requires_approval: false
  • risk: low

Capability-specific rules:

  • NEVER modify the target during observation
  • Do not access targets outside authorized scope
  • Report access failures rather than attempting workarounds
  • Note uncertainty when observations may be stale or incomplete

Composition Patterns

Commonly follows:

  • search - Observe specific targets found through search
  • retrieve - Observe content retrieved by reference

Commonly precedes:

  • state - Observations feed into world state modeling
  • detect - Observations provide data for pattern detection
  • compare - Observations enable comparison with expected state

Anti-patterns:

  • Never use observe for modification (use mutate)
  • Avoid observe for pattern matching (use detect)

Workflow references:

  • See reference/workflow_catalog.yaml#debug_code_change for observation in debugging
  • See reference/workflow_catalog.yaml#world_model_build for observation in modeling

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.