Agent skill
backlog-tools-administrator
Administer the backlog tooling ecosystem when a capability gap is discovered. Invoke when backlog.py, backlog skills, or backlog agents lack a needed operation and a workaround was used or is about to be used. Classifies gaps as script (delegates to @python-cli-architect), process (loads improve-processes), or documentation (delegates to @contextual-ai-documentation-optimizer). Domain: backlog.py, create/work/groom-backlog-item skills, backlog-item-groomer agent, hooks, templates, references, rules, and tests.
Install this agent skill to your Project
npx add-skill https://github.com/Jamie-BitFlight/claude_skills/tree/main/.claude/skills/backlog-tools-administrator
SKILL.md
<gap_description>$ARGUMENTS</gap_description>
Backlog Tools Administrator
Close capability gaps in the backlog tooling ecosystem instead of bypassing the backlog tools (MCP or CLI) with direct file edits or gh commands.
Arguments
<gap_description/> — free-text description of the capability gap. Example: backlog.py update has no --title or --description flag.
When This Skill Activates
- Agent discovers
backlog.pylacks a subcommand or flag for a needed operation - Agent is about to use
Write/Editon a.claude/backlog/*.mdfile directly - Agent is about to use
gh issue editinstead of the backlog script - User reports a process gap or workaround in the backlog workflow
- Post-mortem on a process violation involving backlog tooling
Domain
All files listed in ./references/domain-registry.md. Changes outside this registry are out of scope for this skill.
Workflow
flowchart TD
Start(["Gap reported: <gap_description/>"]) --> S1["Step 1 — Identify the gap"]
S1 --> S2{"Step 2 — Classify gap type"}
S2 -->|"Script — backlog.py missing<br>subcommand, flag, or behavior"| Script["Step 3A — Script fix"]
S2 -->|"Process — CLAUDE.md rule,<br>skill workflow, or state machine<br>is incomplete or ambiguous"| Process["Step 3B — Process fix"]
S2 -->|"Documentation — skill SKILL.md,<br>agent prompt, or reference file<br>needs update"| Docs["Step 3C — Documentation fix"]
S2 -->|"Multiple — gap spans<br>more than one category"| Multi["Step 3D — Multi-category fix"]
Script --> S4["Step 4 — Validate fix"]
Process --> S4
Docs --> S4
Multi --> S4
S4 --> S5["Step 5 — Update domain registry"]
Step 1: Identify the Gap
Describe concretely:
- What operation was needed — the action the agent or user tried to perform
- What exists today — the closest available capability in the backlog tooling
- What workaround was used (if any) — the bypass that violated process
- Impact — what broke or could break due to the gap (sync drift, data loss, process violation)
Read the domain registry to confirm the gap is within scope.
Step 2: Classify the Gap
flowchart TD
Q1{"Does the gap require<br>new or modified Python code<br>in the backlog tooling (MCP server or CLI)?"} -->|Yes| Script["SCRIPT gap"]
Q1 -->|No| Q2{"Does the gap require<br>changing a rule, workflow step,<br>or state transition?"}
Q2 -->|Yes| Process["PROCESS gap"]
Q2 -->|No| Q3{"Does the gap require<br>updating skill instructions,<br>agent prompts, or references?"}
Q3 -->|Yes| Docs["DOCUMENTATION gap"]
Q3 -->|No| OOS["OUT OF SCOPE — report to user"]
Step 3A: Script Fix
For gaps requiring changes to the backlog tooling (MCP server or CLI).
Extension architecture: Both server.py and backlog.py are thin wrappers over operations.py. New capabilities must be added in dependency order:
- Primary: Extend
operations.pywith the new function — this is the single source of business logic. - Secondary (MCP): Add
@mcp.tool()wrapper inserver.pyto expose the new operation as an MCP tool. - Secondary (CLI): Add a subcommand in
backlog.pyto expose the new operation via the CLI.
Delegation:
-
Task is implementing the script fix with
subagent_type="python3-development:python-cli-architect"Context to include in the prompt:.claude/skills/backlog/backlog_core/operations.py(primary business logic),.claude/skills/backlog/backlog_core/server.py(MCP tool definitions),.claude/skills/backlog/scripts/backlog.py(CLI wrapper),.claude/skills/backlog/tests/test_backlog_gh_first.py(existing tests), the gap description from Step 1, and.claude/skills/backlog/references/item-schema.md(frontmatter schema) Output: modifiedoperations.pywith new function,server.pywith@mcp.tool()wrapper,backlog.pywith CLI subcommand, passing tests, linting clean -
After the agent completes, verify the fix:
bashuv run prek run --files .claude/skills/backlog/backlog_core/operations.py .claude/skills/backlog/backlog_core/server.py .claude/skills/backlog/scripts/backlog.py uv run pytest .claude/skills/backlog/tests/ -
Update the
backlogskill SKILL.md to document the new MCP tool and CLI subcommand — proceed to Step 3C.
Step 3B: Process Fix
For gaps requiring changes to rules, workflow steps, or state transitions.
-
Load the
improve-processesskill for process quality methodology:textSkill(skill: "improve-processes") -
Read the affected process file(s) from the domain registry.
-
Apply the improve-processes triage protocol and excellence checklist to the modified process.
-
Write the corrected process using
Editon the affected file (CLAUDE.md section, skill SKILL.md, or reference file). -
If the process change affects a skill's workflow, delegate the skill edit to Step 3C.
Step 3C: Documentation Fix
For gaps requiring changes to skill instructions, agent prompts, or reference files.
- Task is optimizing the affected documentation with
subagent_type="plugin-creator:contextual-ai-documentation-optimizer"Context to include in the prompt: the file to modify (skill SKILL.md, agent .md, or reference .md), the gap description from Step 1, andplugins/plugin-creator/skills/claude-skills-overview-2026/SKILL.mdandplugins/plugin-creator/skills/hooks-guide/SKILL.mdas structural references when modifying skills or hooks Output: updated file with the gap addressed, CoVe verification passing
Step 3D: Multi-Category Fix
When the gap spans multiple categories, execute steps in dependency order:
- Script first (Step 3A) — new capabilities must exist before processes can reference them
- Process second (Step 3B) — rules must be updated before documentation describes them
- Documentation last (Step 3C) — skill/agent docs reflect the final state
Step 4: Validate the Fix
Verify the gap is closed:
-
Script changes:
bashuv run prek run --files <modified-files> uv run pytest .claude/skills/backlog/tests/For MCP tool additions: call the new
mcp__plugin_dh_backlog__<tool_name>tool with valid parameters and confirm the returned dict contains expected result keys (not anerrorkey). -
Process changes: confirm the new rule/workflow handles the original gap scenario without ambiguity.
-
Documentation changes: confirm the updated instructions would have prevented the original workaround.
Report what changed:
GAP: {original gap description}
TYPE: {SCRIPT|PROCESS|DOCUMENTATION|MULTI}
FILES CHANGED:
- {file path}: {what changed}
VALIDATION: {PASS|FAIL — with details}
Step 5: Update Domain Registry
If new files were created (new reference, new test, new script), update ./references/domain-registry.md to include them.
Completion Criteria
- Gap identified with concrete description (operation, existing capability, workaround, impact)
- Gap classified as SCRIPT, PROCESS, DOCUMENTATION, or MULTI
- Fix delegated to appropriate agent (not implemented inline)
- Script changes pass tests and linting
- Process changes satisfy improve-processes excellence checklist
- Documentation changes pass CoVe verification
- Domain registry updated if new files were created
- Report delivered showing what changed and validation status
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
delegate
Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Agent tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.
swarm-spawning
Spawn agents and teammates in Claude Code swarms. Use when choosing between subagents vs teammates, selecting agent types (Explore, Plan, general-purpose, plugin agents), configuring spawn backends (in-process, tmux, iterm2), or setting environment variables for spawned agents.
knowledge-explorer
Manage the research/ knowledge base (KB) of tool and library research entries. Use when browsing KB topics, adding new research entries, updating existing entries with dated revisions, fetching GitHub repo metadata into a draft KB entry, or migrating old-format entries to skill-spec frontmatter. Triggers on tasks like "what do we have on X", "add this to the KB", "update the KB entry for Y", "fetch github info for owner/repo", or "migrate old entries".
design-anti-patterns
Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents "Codex UI" — the generic AI aesthetic of soft gradients, floating panels, oversized rounded corners, glassmorphism, hero sections in dashboards, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy: functional, honest, human-designed interfaces. Triggers on: UI generation, dashboard building, frontend component creation, CSS styling, landing page design, or any task producing visual interface code.
Didn't find tool you were looking for?