mcpbeat Sign in

Fixdocs Agent Skill

Fix Terraform provider end user documentation issues detected by swissshepherd (ss). Removes an ignored target from the config, runs ss, validates findings, fixes the documentation, and commits.

2k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
11023
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/hashicorp/terraform-provider-aws --skill fixdocs

The instruction itself

14 sections, as written by the author

<!-- Copyright IBM Corp. 2014, 2026 -->

<!-- SPDX-License-Identifier: MPL-2.0 -->

Skill: Fix End User Documentation With swissshepherd

Fix Terraform provider documentation issues by removing targets from the swissshepherd ignore list, validating findings against the schema, and correcting the documentation.

When to use

Trigger this skill when the user:

  • Says "fix docs", "fixdocs", "run swissshepherd", "run ss", or similar
  • Asks to remove a target from the swissshepherd ignore list
  • Asks to fix documentation for a specific resource or data source
  • Provides swissshepherd output and asks to fix the findings

Inputs

Optional:

  • A target name (e.g., aws_s3_bucket) or prefix (e.g., aws_s3_)
  • A type (resource, data_source, ephemeral, etc.)
  • Number of targets to process (default: 1)

If no target is specified, pick the next one from ignore_targets in .ci/swissshepherd-weak.hcl.

Procedure

Phase 1: Verify clean baseline

make swissshepherd

This MUST output "All checks passed." before proceeding. If it doesn't, stop and tell the user the baseline is dirty.

Phase 2: Select and expose target

  • Open .ci/swissshepherd-weak.hcl
  • Find the target in an ignore_targets list (within a check block)
  • Remove the target line from the list
  • Run swissshepherd to see findings:
swissshepherd --config .ci/swissshepherd-weak.hcl --target <name> --type <type>

If "All checks passed" — the target was already clean. Commit the config removal and move to the next target.

Phase 3: Validate findings

For each finding, determine if it's valid by checking the schema source of truth:

  • Coverage errors ("not documented", "does not exist in schema"): Read the resource's Go source (internal/service/<service>/<resource>.go or *_data_source.go) to confirm the attribute/block exists in the schema.
  • Heading errors: Check what the heading currently says vs what ss expects.
  • Label errors: Check if the attribute is Required, Optional, or Computed in the schema.
  • Byline errors: Compare against the expected bylines in the config.

If a finding appears to be a swissshepherd bug (schema says one thing, ss reports another), note it and skip — do NOT fix the doc incorrectly.

Phase 4: Fix the documentation

BOTH WARNINGS AND ERRORS should be fixed!!

Open the doc file (path is in the ss output) and apply fixes:

| Finding | Fix |

|---------|-----|

| "block X is not documented" | Add a ### \block_name\ Block section with its attributes listed |

| "attribute X should be documented in Attribute Reference" | Add to Attribute Reference section |

| "attribute X should not appear in Argument Reference" | Move from Arguments to Attributes |

| "documented attribute X does not exist in schema" | Remove from docs (it's phantom) |

| "missing (Required) or (Optional) label" | Add the correct label based on schema |

| "heading ... should be ..." | Rename to the suggested heading |

| "byline does not match expected texts" | Replace with a standard byline |

| "reference-style link definition" | Convert ref]: url to inline [text |

Documentation style rules

When adding or editing documentation:

  • Arguments: * \name\ - (Required) Description. or * \name\ - (Optional) Description.
  • Attributes: * \name\ - Description. (no Required/Optional label)
  • Descriptions start with a verb or noun — never "A ", "An ", "The ", "Specifies ", "Indicates "
  • Boolean arguments: start with "Whether to..."
  • Keep alphabetical order within required/optional groups
  • Block sections use heading: ### block_name Block
  • Byline for arguments: "The following arguments are required:" / "The following arguments are optional:"
  • Byline for attributes: "In addition to all arguments above, the following attributes are exported:"

Authoritative reference: docs/end-user-documentation.md. When this skill and that document disagree, the document wins.

Phase 5: Verify fix

swissshepherd --config .ci/swissshepherd-weak.hcl --target <name> --type <type>

Must output "All checks passed." If not, iterate on remaining findings.

Phase 6: Full verification

make swissshepherd

Must output "All checks passed." to confirm no regressions.

Phase 7: Commit

Stage and commit:

git add .ci/swissshepherd-weak.hcl website/docs/
git commit -m "<resource_name>: Fix documentation per swissshepherd"

Use the resource name without the aws_ prefix in the commit message scope when it matches a single service. For multi-target batches, use the service name.

Important constraints

  • Schema is truth. Never "fix" a finding by silencing it if the schema confirms the issue.
  • One target per commit. Each removed ignore target gets its own commit for clean git history.
  • Always use --config .ci/swissshepherd-weak.hcl — running without config produces 20,000+ findings.
  • Check both check blocks. A target may appear in ignore_targets under check "schema_docs" AND check "import_section" (or others). Remove from all.
  • Don't touch ignore_contents_check unless the user explicitly asks — those are structural exceptions.
  • Preserve file structure. Don't rewrite entire doc files. Make minimal, targeted edits.
  • Nested blocks. When ss reports "block X.Y is not documented", the doc needs a subsection under the parent block's section. Use ### y Block nested contextually after the parent.

Example session

User: "fix docs for aws_s3_bucket_lifecycle_configuration"

  • Verify make swissshepherd passes
  • Remove aws_s3_bucket_lifecycle_configuration from ignore_targets in the schema_docs check block
  • Run swissshepherd --config .ci/swissshepherd-weak.hcl --target aws_s3_bucket_lifecycle_configuration --type resource
  • See: ERROR [schema_docs] ... block "rule.filter" is not documented
  • Check Go source — confirm filter block exists under rule
  • Add ### filter Block section with its attributes
  • Re-run ss — passes
  • Run make swissshepherd — passes
  • Commit

Other skills for the same job

different authors, same section of the catalogue
Azure Kubernetes Automatic Readiness
by microsoft
vendor ×3

Assess Kubernetes workloads and cluster configuration for AKS Automatic compatibility. Identifies incompatibilities, generates fixes, and guides migration from AKS Standard to AKS Automatic. WHEN: migrate to AKS Automatic, check AKS Automatic readiness, validate manifests for Automatic, assess cluster for Automatic compatibility, fix deployment for Automatic compatibility, identify AKS Automatic migration blockers, is my cluster ready for AKS Automatic.

13k tokens
Capacity
by microsoft
vendor ×3

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

6k tokens scripts
Customize
by microsoft
vendor ×3

Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard/Standard/ProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).

8k tokens
Deploy Model
by microsoft
vendor ×3

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

26k tokens scripts
Preset
by microsoft
vendor ×3

Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).

9k tokens
Lamindb
by christophacham
×3

This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. Use when managing biological datasets (scRNA-seq, spatial, flow cytometry, etc.), tracking computational workflows, curating and validating data with biological ontologies, building data lakehouses, or ensuring data lineage and reproducibility in biological research. Covers data management, annotation, ontologies (genes, cell types, diseases, tissues), schema validation, integrations with workflow managers (Nextflow, Snakemake) and MLOps platforms (W&B, MLflow), and deployment strategies.

22k tokens
Latchbio Integration
by christophacham
×3

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

12k tokens
Modal
by christophacham
×3

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

17k tokens

How to use it

Copy the folder

Take hashicorp/fixdocs from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.