Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

cli-anything-firefly-iii

Firefly III CLI - Personal finance management via CLI-Anything

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./firefly-iii/agent-harness/cli_anything/firefly_iii/skills/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is exceptionally actionable — every command, configuration, workflow, and error path is concrete and copy-paste ready — but it is a monolithic reference manual rather than a skill overview. Repetitive per-entity example blocks, a comparison table, and a full API checklist bloat the token budget, and the lack of any offloaded reference files or validation around destructive operations keeps workflow clarity and structure mid-range.

Suggestions

Collapse the 17 per-entity example sections (especially the 14 autocomplete lines) into the command-group table plus one or two exemplar patterns, moving the full command reference to a separate commands.md reference file.

Add validation checkpoints to destructive workflows, e.g. verify a transaction with `transactions get --id <id>` before `transactions delete`, and re-check `info status` after bulk operations.

Trim meta-content Claude does not need (the MCP comparison table, the 28-item API coverage checklist, the License section) or move the API coverage list into a reference file.

Dimension	Reasoning	Score
Conciseness	The body is ~700 lines dominated by seventeen near-identical per-entity CRUD example blocks — including 14 consecutive autocomplete commands and a full CRUD set for every command group — that mostly restate the command-group table, plus an MCP comparison table and a 28-item API checklist. This is noticeably verbose with several padded/redundant sections (anchor 2) rather than 'severely verbose' concept explanation (anchor 1), but well below anchor 3's 'mostly efficient'.	2 / 5
Actionability	Everything is concrete and executable: install command, prerequisites, env-var and CLI configuration, copy-paste-ready commands with real flags and values for every operation, five named multi-step workflows with exact commands, and troubleshooting with actual error messages. This matches anchor 5 (fully executable, copy-paste ready, examples covering the common cases).	5 / 5
Workflow Clarity	The Agent Guidelines workflows (view balances, record expense, recurring budget, automation rule, monthly report) are numbered with concrete commands and an upfront `info status` connection check, but there are no post-operation verification steps, and destructive `delete` operations appear throughout with no validation or confirmation guidance — the cap at 3 for destructive/batch operations without validation applies. Not anchor 4 because checkpoints beyond the initial connection check are missing entirely.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent), so a ~500-line command/API reference that clearly belongs in a separate file is fully inlined in SKILL.md. Section headers are clear and consistent throughout (better than anchor 2's 'no section headers' example), matching anchor 3: structure is present but content that should be separate is inline.	3 / 5
	Total	13 / 20 Passed

Description

48%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies the product and domain clearly but reads like a package title rather than a skill description: it states no concrete capabilities, omits any 'Use when...' trigger guidance, and lacks natural finance keywords like budget or transactions. It is distinguishable from other skills mainly because 'Firefly III' is a niche product name, not because the description does trigger work.

Suggestions

List 3-5 concrete capabilities, e.g. 'Manage accounts, transactions, budgets, and bills; generate expense/income reports and recurring transactions' instead of the generic 'Personal finance management'.

Add an explicit trigger clause, e.g. 'Use when the user mentions Firefly III or asks to record expenses, track budgets, or manage personal-finance data via the Firefly III API'.

Include natural synonyms users would say (budgeting, expenses, net worth, savings goals/piggy banks) so the description surfaces those queries.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Firefly III", "Personal finance management") but lists no concrete actions such as managing accounts, creating transactions, or generating budgets/reports. It matches anchor 2 ('names the domain but actions are minimal or generic') and falls short of anchor 3, which requires 1-2 concrete actions.	2 / 5
Completeness	The 'what' is reasonably clear (a CLI for personal finance management via Firefly III), but there is no 'Use when...' clause or any trigger guidance for when Claude should invoke it, which caps completeness at 3 per the judging guidelines. It is not anchor 4 because 'when' is entirely absent rather than merely imprecise.	3 / 5
Trigger Term Quality	"Firefly III" and "personal finance management" are relevant keywords a user might say, but common natural phrases users would actually use (budget, transactions, expenses, reports, net worth) are missing. This matches anchor 3 ('some relevant keywords but missing common variations or synonyms') and not anchor 4, since keyword coverage is thin rather than good.	3 / 5
Distinctiveness Conflict Risk	"Firefly III" identifies a specific niche tool with distinct triggers, but the broad phrase "Personal finance management" overlaps with generic budgeting/finance skills. This sits between anchor 4 (mostly distinct, minor overlap risk) and anchor 5 (clear niche, minimal conflict) — the product name is distinct, yet the generic finance phrasing keeps some overlap risk, so 4 fits best.	4 / 5
	Total	12 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (710 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: HKUDS/CLI-Anything
Path: firefly-iii/agent-harness/cli_anything/firefly_iii/skills/SKILL.md
Revision: 34f5195

Reviewed: 22 days ago

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

cli-anything-firefly-iii

Table of Contents

Is this your skill?